Phi-4 14B — how much card memory it needs
Whether a quantised model file fits entirely in a graphics card's memory. It is not a statement about whether the model will run, how fast it will run, or how good its output will be.
These figures are calculated from published file sizes and model architecture. No combination on this site has been tested on physical hardware.
How much card memory it needs
| Component | Size | Where the figure comes from |
|---|---|---|
| Quantised file (Q4_K_M) | 8.3 GiB | Measured: the size of the file actually distributed (8,890,306,112 bytes) |
| Key/value cache at 4,096 tokens | 0.8 GiB | Calculated from the model architecture under the assumptions below |
| Key/value cache at 32,768 tokens | 6.2 GiB | Calculated from the model architecture under the assumptions below |
| Runtime overhead | 1.0 GiB | Assumed: a flat allowance for compute buffers, the driver context and the display |
| Required at 4,096 tokens | 10.1 GiB | Sum of the above |
| Required at 32,768 tokens | 15.6 GiB | Sum of the above |
| Weights and overhead only | 9.3 GiB | The floor, if the key/value cache is set aside |
The arithmetic, so you can redo it
GiB (1024^3 bytes). Card memory advertised as '8GB' is treated as 8 GiB so the two are comparable.
required_vram_gib= quantised_file_size + kv_cache + runtime_overheadkv_cache_bytes= 2 (key and value) * 2 bytes * num_kv_heads * head_dim * sum(tokens held per layer)tokens_held_full_attention= num_layers * context_tokenstokens_held_with_sliding_window= (num_layers - sliding_window_layers) * context_tokens + sliding_window_layers * min(context_tokens, sliding_window_tokens)
| Input for this model | Value |
|---|---|
| Layers | 40 |
| Key/value heads | 10 |
| Head dimension | 128 |
| Sliding window | Full attention on every layer |
| Context length the model publishes | 16,384 tokens |
| Distributed file | phi-4-Q4_K_M.gguf |
| Distributor | Unsloth (community), unsloth/phi-4-GGUF |
Measured
- The size in bytes of the quantised file that is actually distributed.
- Model architecture: layer count, key/value head count, head dimension, sliding-window width.
- Card memory size as published by the graphics vendor.
Assumed
- The key/value cache is held at 16-bit precision for every token.
- Two context lengths are assumed: 4,096 and 32,768 tokens.
- A flat 1.0 GiB is set aside for compute buffers, the driver context and the display.
Graphics cards with room for it
| Card | Card memory | Outcome | The arithmetic | Confidence |
|---|---|---|---|---|
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition | 96 GB | ✓ Fits in VRAM Estimated | 96 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA A100 80GB PCIe | 80 GB | ✓ Fits in VRAM Estimated | 80 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA H100 PCIe | 80 GB | ✓ Fits in VRAM Estimated | 80 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA A40 | 48 GB | ✓ Fits in VRAM Estimated | 48 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA L40 | 48 GB | ✓ Fits in VRAM Estimated | 48 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA L40S | 48 GB | ✓ Fits in VRAM Estimated | 48 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Quadro RTX 8000 | 48 GB | ✓ Fits in VRAM Estimated | 48 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA RTX 6000 Ada Generation | 48 GB | ✓ Fits in VRAM Estimated | 48 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA RTX A6000 | 48 GB | ✓ Fits in VRAM Estimated | 48 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA A100 40GB PCIe | 40 GB | ✓ Fits in VRAM Estimated | 40 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon Pro W6800 | 32 GB | ✓ Fits in VRAM Estimated | 32 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 5090 (Reference design) | 32 GB | ✓ Fits in VRAM Estimated | 32 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA RTX 5000 Ada Generation | 32 GB | ✓ Fits in VRAM Estimated | 32 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA RTX PRO 4500 Blackwell | 32 GB | ✓ Fits in VRAM Estimated | 32 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Tesla V100 PCIe 32GB | 32 GB | ✓ Fits in VRAM Estimated | 32 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 7900 XTX (Reference design) | 24 GB | ✓ Fits in VRAM Estimated | 24 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 3090 (Reference design) | 24 GB | ✓ Fits in VRAM Estimated | 24 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 3090 Ti (Reference design) | 24 GB | ✓ Fits in VRAM Estimated | 24 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 4090 (Reference design) | 24 GB | ✓ Fits in VRAM Estimated | 24 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA A10 | 24 GB | ✓ Fits in VRAM Estimated | 24 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA A30 | 24 GB | ✓ Fits in VRAM Estimated | 24 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA L4 | 24 GB | ✓ Fits in VRAM Estimated | 24 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Quadro M6000 24GB (Reference design) | 24 GB | ✓ Fits in VRAM Estimated | 24 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: this card's memory size is recorded here from material whose source the record does not identify, so grade E is shown alongside B. | BE |
| NVIDIA Quadro P6000 (Reference design) | 24 GB | ✓ Fits in VRAM Estimated | 24 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: this card's memory size is recorded here from material whose source the record does not identify, so grade E is shown alongside B. | BE |
| NVIDIA Quadro RTX 6000 | 24 GB | ✓ Fits in VRAM Estimated | 24 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA RTX 3090 | 24 GB | ✓ Fits in VRAM Estimated | 24 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA RTX 3090TI | 24 GB | ✓ Fits in VRAM Estimated | 24 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA RTX 4500 Ada Generation | 24 GB | ✓ Fits in VRAM Estimated | 24 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA RTX A5000 | 24 GB | ✓ Fits in VRAM Estimated | 24 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA RTX A5500 | 24 GB | ✓ Fits in VRAM Estimated | 24 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA RTX PRO 4000 Blackwell | 24 GB | ✓ Fits in VRAM Estimated | 24 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA TITAN RTX (Reference design) | 24 GB | ✓ Fits in VRAM Estimated | 24 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Tesla M40 24GB | 24 GB | ✓ Fits in VRAM Estimated | 24 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Tesla P40 | 24 GB | ✓ Fits in VRAM Estimated | 24 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 7900 XT (Reference design) | 20 GB | ✓ Fits in VRAM Estimated | 20 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA RTX 4000 Ada Generation | 20 GB | ✓ Fits in VRAM Estimated | 20 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA RTX 4000 SFF Ada Generation | 20 GB | ✓ Fits in VRAM Estimated | 20 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA RTX A4500 | 20 GB | ✓ Fits in VRAM Estimated | 20 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 6800 (Reference design) | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 6800 XT (Reference design) | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 6900 XT | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 6900 XT (Reference design) | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 6950 XT (Reference design) | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 7600 XT (Reference design) | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 7800 XT (Reference design) | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 7900 GRE (Reference design) | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 9060 XT (Reference design) | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 9070 (Reference design) | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 9070 XT (Reference design) | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon VII (Reference design) | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon Vega Frontier Edition (Reference design) | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: this card's memory size is recorded here from material whose source the record does not identify, so grade E is shown alongside B. | BE |
| GeForce RTX 4060 Ti (Reference design), 16 GB | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 4070 Ti SUPER (Reference design) | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 4080 (Reference design) | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 4080 SUPER (Reference design) | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 5060 Ti (Reference design), 16 GB | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 5070 Ti (Reference design) | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 5080 (Reference design) | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| Intel Arc A770 (Reference design), 16 GB | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA A16 | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Quadro P5000 (Reference design) | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Quadro RTX 5000 | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA RTX 2000 Ada Generation | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA RTX A4000 | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA T4 | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Tesla P100 PCIe 16GB | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Tesla V100 PCIe 16GB | 16 GB | ✓ Fits in VRAM Estimated | 16 GB of memory is at least the 15.6 GB required at a context length of 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 6700 XT (Reference design) | 12 GB | △ Fits at short context only Estimated | 12 GB of memory covers the 10.1 GB required at a context length of 4,096 tokens, but not the 15.6 GB required at 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 6750 XT (Reference design) | 12 GB | △ Fits at short context only Estimated | 12 GB of memory covers the 10.1 GB required at a context length of 4,096 tokens, but not the 15.6 GB required at 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 7700 XT (Reference design) | 12 GB | △ Fits at short context only Estimated | 12 GB of memory covers the 10.1 GB required at a context length of 4,096 tokens, but not the 15.6 GB required at 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX TITAN X (Reference design) | 12 GB | △ Fits at short context only Estimated | 12 GB of memory covers the 10.1 GB required at a context length of 4,096 tokens, but not the 15.6 GB required at 32,768 tokens. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 2060 12GB (Reference design) | 12 GB | △ Fits at short context only Estimated | 12 GB of memory covers the 10.1 GB required at a context length of 4,096 tokens, but not the 15.6 GB required at 32,768 tokens. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 3080 (Reference design), 12 GB | 12 GB | △ Fits at short context only Estimated | 12 GB of memory covers the 10.1 GB required at a context length of 4,096 tokens, but not the 15.6 GB required at 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 3080 Ti (Reference design) | 12 GB | △ Fits at short context only Estimated | 12 GB of memory covers the 10.1 GB required at a context length of 4,096 tokens, but not the 15.6 GB required at 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 4070 (Reference design) | 12 GB | △ Fits at short context only Estimated | 12 GB of memory covers the 10.1 GB required at a context length of 4,096 tokens, but not the 15.6 GB required at 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 4070 SUPER (Reference design) | 12 GB | △ Fits at short context only Estimated | 12 GB of memory covers the 10.1 GB required at a context length of 4,096 tokens, but not the 15.6 GB required at 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 4070 Ti (Reference design) | 12 GB | △ Fits at short context only Estimated | 12 GB of memory covers the 10.1 GB required at a context length of 4,096 tokens, but not the 15.6 GB required at 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 5070 (Reference design) | 12 GB | △ Fits at short context only Estimated | 12 GB of memory covers the 10.1 GB required at a context length of 4,096 tokens, but not the 15.6 GB required at 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| Intel Arc B580 (Reference design) | 12 GB | △ Fits at short context only Estimated | 12 GB of memory covers the 10.1 GB required at a context length of 4,096 tokens, but not the 15.6 GB required at 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Quadro M6000 (Reference design) | 12 GB | △ Fits at short context only Estimated | 12 GB of memory covers the 10.1 GB required at a context length of 4,096 tokens, but not the 15.6 GB required at 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA RTX 3080TI | 12 GB | △ Fits at short context only Estimated | 12 GB of memory covers the 10.1 GB required at a context length of 4,096 tokens, but not the 15.6 GB required at 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA RTX A2000 12GB | 12 GB | △ Fits at short context only Estimated | 12 GB of memory covers the 10.1 GB required at a context length of 4,096 tokens, but not the 15.6 GB required at 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA TITAN V (Reference design) | 12 GB | △ Fits at short context only Estimated | 12 GB of memory covers the 10.1 GB required at a context length of 4,096 tokens, but not the 15.6 GB required at 32,768 tokens. This outcome is no stronger than the figures it was calculated from: this card's memory size is recorded here from material whose source the record does not identify, so grade E is shown alongside B. | BE |
| NVIDIA TITAN Xp (Reference design) | 12 GB | △ Fits at short context only Estimated | 12 GB of memory covers the 10.1 GB required at a context length of 4,096 tokens, but not the 15.6 GB required at 32,768 tokens. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| PALIT GeForce RTX 3060 Infinity 2 OC | 12 GB | △ Fits at short context only Estimated | 12 GB of memory covers the 10.1 GB required at a context length of 4,096 tokens, but not the 15.6 GB required at 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 1080 Ti (Reference design) | 11 GB | △ Fits at short context only Estimated | 11 GB of memory covers the 10.1 GB required at a context length of 4,096 tokens, but not the 15.6 GB required at 32,768 tokens. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 2080 Ti (Reference design) | 11 GB | △ Fits at short context only Estimated | 11 GB of memory covers the 10.1 GB required at a context length of 4,096 tokens, but not the 15.6 GB required at 32,768 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 550X Discrete GDDR5 | Not published | ? Unverified | The memory size of this graphics option is not stated in the cited specification, so no verdict is given. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 6500XT Discrete | Not published | ? Unverified | The memory size of this graphics option is not stated in the cited specification, so no verdict is given. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 1660 Discrete [gtx-1660-6gb] | Not published | ? Unverified | The memory size of this graphics option is not stated in the cited specification, so no verdict is given. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 1660 Discrete [gtx-1660-super-6gb] | Not published | ? Unverified | The memory size of this graphics option is not stated in the cited specification, so no verdict is given. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 3060 Discrete GDDR6 | Not published | ? Unverified | The memory size of this graphics option is not stated in the cited specification, so no verdict is given. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 3070 Discrete GDDR6X | Not published | ? Unverified | The memory size of this graphics option is not stated in the cited specification, so no verdict is given. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 6700 (Reference design) | 10 GB | ✕ Exceeds VRAM Estimated | 10 GB of memory is below the 10.1 GB required at a context length of 4,096 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 3080 (Reference design), 10 GB | 10 GB | ✕ Exceeds VRAM Estimated | 10 GB of memory is below the 10.1 GB required at a context length of 4,096 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| Intel Arc B570 (Reference design) | 10 GB | ✕ Exceeds VRAM Estimated | 10 GB of memory is below the 10.1 GB required at a context length of 4,096 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA RTX 3080 | 10 GB | ✕ Exceeds VRAM Estimated | 10 GB of memory is below the 10.1 GB required at a context length of 4,096 tokens. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon Pro W6600 | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon R9 390 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 480 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 5500 XT (Reference design), 8 GB | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 5700 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 5700 XT (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 580 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 590 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 6600 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 6600 LE Discrete 8GB GDDR6 | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 6600 XT (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 6650 XT (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 7600 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 9050 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX Vega 56 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX Vega 64 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 1070 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 1070 Ti (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 1080 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 2060 SUPER (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 2070 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 2070 SUPER (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 2080 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 2080 SUPER (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 3050 8GB (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 3060 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 3060 Ti (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 3070 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 3070 Ti (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 4060 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 4060 OC Low Profile 8G (GV-N4060OC-8GL) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 4060 Ti (Reference design), 8 GB | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 5050 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 5060 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 5060 Ti (Reference design), 8 GB | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 5060 Ti 8G VENTUS 2X PLUS | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| Intel Arc A580 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| Intel Arc A750 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| Intel Arc A770 (Reference design), 8 GB | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA GeForce RTX 3050 Discrete 8GB GDDR6 | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA GeForce RTX 4060 Discrete 8G GDDR6 | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size is recorded here from material whose source the record does not identify, so grade E is shown alongside B. | BE |
| NVIDIA GeForce RTX 5050 Discrete 8GB GDDR6 | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA GeForce RTX 5060 Discrete 8G GDDR7 | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size is recorded here from material whose source the record does not identify, so grade E is shown alongside B. | BE |
| NVIDIA Quadro M4000 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Quadro M5000 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Quadro P4000 (Reference design) | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Quadro RTX 4000 | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA RTX A1000 | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA T1000 | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Tesla P4 | 8 GB | ✕ Exceeds VRAM Estimated | 8 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size is recorded here from material whose source the record does not identify, so grade E is shown alongside B. | BE |
| AMD Radeon RX 5600 XT (Reference design) | 6 GB | ✕ Exceeds VRAM Estimated | 6 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 1060 (Reference design) | 6 GB | ✕ Exceeds VRAM Estimated | 6 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 1660 (Reference design) | 6 GB | ✕ Exceeds VRAM Estimated | 6 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 1660 SUPER (Reference design) | 6 GB | ✕ Exceeds VRAM Estimated | 6 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 1660 Ti (Reference design) | 6 GB | ✕ Exceeds VRAM Estimated | 6 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 980 Ti (Reference design) | 6 GB | ✕ Exceeds VRAM Estimated | 6 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX TITAN (Reference design) | 6 GB | ✕ Exceeds VRAM Estimated | 6 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX TITAN Black (Reference design) | 6 GB | ✕ Exceeds VRAM Estimated | 6 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 2060 (Reference design) | 6 GB | ✕ Exceeds VRAM Estimated | 6 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 3050 6GB (Reference design) | 6 GB | ✕ Exceeds VRAM Estimated | 6 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce RTX 3050 OC Low Profile 6G (GV-N3050OC-6GL) | 6 GB | ✕ Exceeds VRAM Estimated | 6 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| Intel Arc A380 (Reference design) | 6 GB | ✕ Exceeds VRAM Estimated | 6 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA GeForce GTX 1060 | 6 GB | ✕ Exceeds VRAM Estimated | 6 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA GeForce RTX 2060 | 6 GB | ✕ Exceeds VRAM Estimated | 6 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA GeForce RTX 3050 Discrete 6GB GDDR6 | 6 GB | ✕ Exceeds VRAM Estimated | 6 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA RTX A2000 6GB | 6 GB | ✕ Exceeds VRAM Estimated | 6 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Quadro P2000 (Reference design) | 5 GB | ✕ Exceeds VRAM Estimated | 5 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Quadro P2200 (Reference design) | 5 GB | ✕ Exceeds VRAM Estimated | 5 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| 4 GB AMD Radeon R7 450 (optional) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size is recorded here from material whose source the record does not identify, so grade E is shown alongside B. | BE |
| AMD Radeon Pro W6400 | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon R9 290 (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon R9 290X (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon R9 Fury (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon R9 Fury X (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon R9 Nano (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 470 (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 550 (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 5500 XT (Reference design), 4 GB | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 560 (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 570 (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 6400 Discrete 4GB GDDR6 | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 6500 XT (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX640 | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size is recorded here from material whose source the record does not identify, so grade E is shown alongside B. | BE |
| GeForce GTX 1050 Ti (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 1630 (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 1650 (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 1650 SUPER (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 970 (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 980 (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| Intel Arc A310 (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| Intel Arc A310 LP Graphics Discrete 4GB GDDR6 | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Quadro K1200 (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Quadro K2200 (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Quadro K4200 (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Quadro M2000 (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Quadro P1000 (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA RTX A400 | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA T1000 (Reference design) | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA T400, 4 GB | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA T600 | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| RD-RX6400-E4GB/LP | 4 GB | ✕ Exceeds VRAM Estimated | 4 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon R9 280 (Reference design) | 3 GB | ✕ Exceeds VRAM Estimated | 3 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon R9 280X (Reference design) | 3 GB | ✕ Exceeds VRAM Estimated | 3 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 780 (Reference design) | 3 GB | ✕ Exceeds VRAM Estimated | 3 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 780 Ti (Reference design) | 3 GB | ✕ Exceeds VRAM Estimated | 3 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| 2 GB AMD Radeon R5 430 (optional) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size is recorded here from material whose source the record does not identify, so grade E is shown alongside B. | BE |
| AMD Radeon 520 | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size is recorded here from material whose source the record does not identify, so grade E is shown alongside B. | BE |
| AMD Radeon 550 | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size is recorded here from material whose source the record does not identify, so grade E is shown alongside B. | BE |
| AMD Radeon R7 240 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon R7 250 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon R7 260X (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon R9 270 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon R9 270X (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon R9 380 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon RX 460 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GT 1010 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GT 1030 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GT 630 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size is recorded here from material whose source the record does not identify, so grade E is shown alongside B. | BE |
| GeForce GT 640 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GT 710 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GT 730 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 1050 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 660 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 660 Ti (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 670 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 680 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 750 Ti (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 760 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 770 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 950 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 960 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| Intel Iris Xe MAX 100 | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size is recorded here from material whose source the record does not identify, so grade E is shown alongside B. | BE |
| NVIDIA GeForce GT 730 | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size is recorded here from material whose source the record does not identify, so grade E is shown alongside B. | BE |
| NVIDIA Quadro K620 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size is recorded here from material whose source the record does not identify, so grade E is shown alongside B. | BE |
| NVIDIA Quadro P400 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Quadro P600 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Quadro P620 (Reference design) | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA T400, 2 GB | 2 GB | ✕ Exceeds VRAM Estimated | 2 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| AMD Radeon 540 | 1 GB | ✕ Exceeds VRAM Estimated | 1 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size is recorded here from material whose source the record does not identify, so grade E is shown alongside B. | BE |
| GeForce GT 610 (Reference design) | 1 GB | ✕ Exceeds VRAM Estimated | 1 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size is recorded here from material whose source the record does not identify, so grade E is shown alongside B. | BE |
| GeForce GT 620 (Reference design) | 1 GB | ✕ Exceeds VRAM Estimated | 1 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size is recorded here from material whose source the record does not identify, so grade E is shown alongside B. | BE |
| GeForce GTX 650 (Reference design) | 1 GB | ✕ Exceeds VRAM Estimated | 1 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 650 Ti (Reference design) | 1 GB | ✕ Exceeds VRAM Estimated | 1 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| GeForce GTX 750 (Reference design) | 1 GB | ✕ Exceeds VRAM Estimated | 1 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: this card's memory size and the size of the model file that is distributed are recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| NVIDIA Quadro K600 (Reference design) | 1 GB | ✕ Exceeds VRAM Estimated | 1 GB of memory is smaller than the 8.28 GB model file itself, so shortening the context does not make it fit in memory. This outcome is no stronger than the figures it was calculated from: the size of the model file that is distributed is recorded here from third-party or community material, so grade D is shown alongside B. | BD |
| Outcome | Meaning |
|---|---|
| ✓ Fits in VRAM | The whole model fits in this card's memory at the assumed working context length. |
| △ Fits at short context only | It fits at the short context length but not at the working context length. |
| ✕ Exceeds VRAM | It does not fit in this card's memory even at the short context length. That is not the same as 'will not run': inference software can keep part of the model in system memory. |
| ? Unverified | A value needed for the calculation is missing, so no verdict is given. |
Desktops that take those cards
Only cards whose memory holds this model are listed, and only machines whose published specifications accept the card.
- NVIDIA RTX A6000 — ✓ Fits in VRAM Estimated Dell Precision 3660 Tower (△ Fits with conditions)
- AMD Radeon Pro W6800 — ✓ Fits in VRAM Estimated Dell Precision 3660 Tower (✓ Fits)
- NVIDIA RTX 5000 Ada Generation — ✓ Fits in VRAM Estimated HP Z2 Tower G9 Workstation (△ Fits with conditions)
- NVIDIA Quadro M6000 24GB (Reference design) — ✓ Fits in VRAM Estimated Dell OptiPlex 7000 Tower (2022) (△ Fits with conditions) · Dell OptiPlex 7080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 7090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex Tower Plus 7010 (2023) (△ Fits with conditions) · Dell Precision 3630 Tower (△ Fits with conditions) · Dell Precision 3680 Tower (△ Fits with conditions) · HP Z2 Tower G5 Workstation (△ Fits with conditions) · HP Z2 Tower G8 Workstation (△ Fits with conditions) · HP Z2 Tower G9 Workstation (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 3 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 4 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 5 (△ Fits with conditions)
- NVIDIA Quadro P6000 (Reference design) — ✓ Fits in VRAM Estimated Dell OptiPlex 7000 Tower (2022) (△ Fits with conditions) · Dell OptiPlex 7080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 7090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex Tower Plus 7010 (2023) (△ Fits with conditions) · Dell Precision 3630 Tower (△ Fits with conditions) · Dell Precision 3680 Tower (△ Fits with conditions) · HP Z2 Tower G5 Workstation (△ Fits with conditions) · HP Z2 Tower G8 Workstation (△ Fits with conditions) · HP Z2 Tower G9 Workstation (△ Fits with conditions) · Lenovo ThinkCentre M90t (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 3 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 4 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 5 (△ Fits with conditions)
- NVIDIA RTX 3090 — ✓ Fits in VRAM Estimated Dell Precision 3660 Tower (✓ Fits)
- NVIDIA RTX 3090TI — ✓ Fits in VRAM Estimated Dell Precision 3660 Tower (✓ Fits)
- NVIDIA RTX A5000 — ✓ Fits in VRAM Estimated Dell OptiPlex 7000 Tower (2022) (△ Fits with conditions) · Dell OptiPlex 7080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 7090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex Tower Plus 7010 (2023) (△ Fits with conditions) · Dell Precision 3630 Tower (△ Fits with conditions) · Dell Precision 3660 Tower (△ Fits with conditions) · Dell Precision 3680 Tower (△ Fits with conditions) · HP Z2 Tower G5 Workstation (△ Fits with conditions) · HP Z2 Tower G8 Workstation (△ Fits with conditions) · HP Z2 Tower G9 Workstation (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 3 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 4 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 5 (△ Fits with conditions)
- NVIDIA RTX A5500 — ✓ Fits in VRAM Estimated Dell OptiPlex 7000 Tower (2022) (△ Fits with conditions) · Dell OptiPlex 7080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 7090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex Tower Plus 7010 (2023) (△ Fits with conditions) · Dell Precision 3630 Tower (△ Fits with conditions) · Dell Precision 3660 Tower (△ Fits with conditions) · Dell Precision 3680 Tower (△ Fits with conditions) · HP Z2 Tower G5 Workstation (△ Fits with conditions) · HP Z2 Tower G8 Workstation (△ Fits with conditions) · HP Z2 Tower G9 Workstation (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 3 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 4 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 5 (△ Fits with conditions)
- NVIDIA RTX 4000 Ada Generation — ✓ Fits in VRAM Estimated HP Z2 Tower G9 Workstation (△ Fits with conditions)
- NVIDIA RTX 4000 SFF Ada Generation — ✓ Fits in VRAM Estimated Dell OptiPlex 3050 Small Form Factor (2017) (△ Fits with conditions) · Dell OptiPlex 3050 Tower (2017) (△ Fits with conditions) · Dell OptiPlex 3060 Small Form Factor (2018) (△ Fits with conditions) · Dell OptiPlex 3060 Tower (2018) (△ Fits with conditions) · Dell OptiPlex 3080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 3090 Small Form Factor (2021) (△ Fits with conditions) · Dell OptiPlex 3090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex 5040 Mini Tower (2015) (△ Fits with conditions) · Dell OptiPlex 5040 Small Form Factor (2015) (△ Fits with conditions) · Dell OptiPlex 5050 Small Form Factor (2017) (△ Fits with conditions) · Dell OptiPlex 5050 Tower (2017) (△ Fits with conditions) · Dell OptiPlex 5060 Small Form Factor (2018) (△ Fits with conditions) · Dell OptiPlex 5060 Tower (2018) (△ Fits with conditions) · Dell OptiPlex 5070 Small Form Factor (2019) (△ Fits with conditions) · Dell OptiPlex 5070 Tower (2019) (△ Fits with conditions) · Dell OptiPlex 5080 Small Form Factor (2020) (△ Fits with conditions) · Dell OptiPlex 5080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 5090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex 7000 Small Form Factor (2022) (△ Fits with conditions) · Dell OptiPlex 7000 Tower (2022) (△ Fits with conditions) · Dell OptiPlex 7040 Mini Tower (2015) (△ Fits with conditions) · Dell OptiPlex 7040 Small Form Factor (2015) (△ Fits with conditions) · Dell OptiPlex 7050 Small Form Factor (2017) (△ Fits with conditions) · Dell OptiPlex 7050 Tower (2017) (△ Fits with conditions) · Dell OptiPlex 7060 Small Form Factor (2018) (△ Fits with conditions) · Dell OptiPlex 7060 Tower (2018) (△ Fits with conditions) · Dell OptiPlex 7070 Small Form Factor (2019) (△ Fits with conditions) · Dell OptiPlex 7070 Tower (2019) (△ Fits with conditions) · Dell OptiPlex 7080 Small Form Factor (2020) (△ Fits with conditions) · Dell OptiPlex 7080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 7090 Small Form Factor (2021) (△ Fits with conditions) · Dell OptiPlex 7090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex Small Form Factor 7010 (2023) (△ Fits with conditions) · Dell OptiPlex Small Form Factor Plus 7010 (2023) (△ Fits with conditions) · Dell OptiPlex Tower 7010 (2023) (△ Fits with conditions) · Dell OptiPlex Tower Plus 7010 (2023) (△ Fits with conditions) · Dell Precision 3630 Tower (△ Fits with conditions) · Dell Precision 3660 Tower (△ Fits with conditions) · Dell Precision 3680 Tower (△ Fits with conditions) · Dell Precision 5820 Tower (△ Fits with conditions) · HP Elite Tower 600 G9 (△ Fits with conditions) · HP Elite Tower 800 G9 (✓ Fits) · HP Pro Tower 400 G9 (△ Fits with conditions) · HP Z2 Small Form Factor G8 Workstation (△ Fits with conditions) · HP Z2 Tower G5 Workstation (△ Fits with conditions) · HP Z2 Tower G8 Workstation (△ Fits with conditions) · HP Z2 Tower G9 Workstation (△ Fits with conditions) · Lenovo ThinkCentre M70t (△ Fits with conditions) · Lenovo ThinkCentre M70t Gen 4 (△ Fits with conditions) · Lenovo ThinkCentre M70t Gen 5 (△ Fits with conditions) · Lenovo ThinkCentre M710 Tower (△ Fits with conditions) · Lenovo ThinkCentre M720 Tower (△ Fits with conditions) · Lenovo ThinkCentre M75t Gen 5 (△ Fits with conditions) · Lenovo ThinkCentre M80t (△ Fits with conditions) · Lenovo ThinkCentre M80t Gen 3 (✓ Fits) · Lenovo ThinkCentre M90t (✓ Fits) · Lenovo ThinkCentre M90t Gen 3 (✓ Fits) · Lenovo ThinkCentre M90t Gen 4 (✓ Fits) · Lenovo ThinkCentre M90t Gen 5 (✓ Fits) · Lenovo ThinkCentre M910 Tower (△ Fits with conditions) · Lenovo ThinkCentre M920 Tower (△ Fits with conditions) · Lenovo ThinkCentre neo 50t Gen 4 (△ Fits with conditions)
- NVIDIA RTX A4500 — ✓ Fits in VRAM Estimated Dell OptiPlex 7000 Tower (2022) (△ Fits with conditions) · Dell OptiPlex 7080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 7090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex Tower Plus 7010 (2023) (△ Fits with conditions) · Dell Precision 3630 Tower (△ Fits with conditions) · Dell Precision 3660 Tower (△ Fits with conditions) · Dell Precision 3680 Tower (△ Fits with conditions) · HP Elite Tower 600 G9 (△ Fits with conditions) · HP Pro Tower 400 G9 (△ Fits with conditions) · HP Z2 Tower G5 Workstation (△ Fits with conditions) · HP Z2 Tower G8 Workstation (△ Fits with conditions) · HP Z2 Tower G9 Workstation (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 3 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 4 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 5 (△ Fits with conditions) · Lenovo ThinkCentre M910 Tower (△ Fits with conditions)
- AMD Radeon RX 6900 XT — ✓ Fits in VRAM Estimated Dell Precision 3660 Tower (✓ Fits)
- AMD Radeon RX 7600 XT (Reference design) — ✓ Fits in VRAM Estimated Dell OptiPlex 7000 Tower (2022) (△ Fits with conditions) · Dell OptiPlex 7080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 7090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex Tower Plus 7010 (2023) (△ Fits with conditions) · Dell Precision 3630 Tower (△ Fits with conditions) · Dell Precision 3680 Tower (△ Fits with conditions) · HP Elite Tower 600 G9 (△ Fits with conditions) · HP Pro Tower 400 G9 (△ Fits with conditions) · HP Z2 Tower G5 Workstation (△ Fits with conditions) · HP Z2 Tower G8 Workstation (△ Fits with conditions) · HP Z2 Tower G9 Workstation (△ Fits with conditions) · Lenovo ThinkCentre M70t Gen 4 (△ Fits with conditions) · Lenovo ThinkCentre M70t Gen 5 (△ Fits with conditions) · Lenovo ThinkCentre M80t Gen 3 (△ Fits with conditions) · Lenovo ThinkCentre M90t (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 3 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 4 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 5 (△ Fits with conditions) · Lenovo ThinkCentre M910 Tower (△ Fits with conditions)
- AMD Radeon RX 9060 XT (Reference design) — ✓ Fits in VRAM Estimated Dell OptiPlex 7000 Tower (2022) (△ Fits with conditions) · Dell OptiPlex 7080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 7090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex Tower Plus 7010 (2023) (△ Fits with conditions) · Dell Precision 3630 Tower (△ Fits with conditions) · Dell Precision 3680 Tower (△ Fits with conditions) · HP Elite Tower 600 G9 (△ Fits with conditions) · HP Pro Tower 400 G9 (△ Fits with conditions) · HP Z2 Tower G5 Workstation (△ Fits with conditions) · HP Z2 Tower G8 Workstation (△ Fits with conditions) · HP Z2 Tower G9 Workstation (△ Fits with conditions) · Lenovo ThinkCentre M70t Gen 4 (△ Fits with conditions) · Lenovo ThinkCentre M70t Gen 5 (△ Fits with conditions) · Lenovo ThinkCentre M80t Gen 3 (△ Fits with conditions) · Lenovo ThinkCentre M90t (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 3 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 4 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 5 (△ Fits with conditions) · Lenovo ThinkCentre M910 Tower (△ Fits with conditions)
- GeForce RTX 4060 Ti (Reference design), 16 GB — ✓ Fits in VRAM Estimated Dell OptiPlex 7000 Tower (2022) (△ Fits with conditions) · Dell OptiPlex 7080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 7090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex Tower Plus 7010 (2023) (△ Fits with conditions) · Dell Precision 3630 Tower (△ Fits with conditions) · Dell Precision 3680 Tower (△ Fits with conditions) · HP Elite Tower 600 G9 (△ Fits with conditions) · HP Pro Tower 400 G9 (△ Fits with conditions) · HP Z2 Tower G5 Workstation (△ Fits with conditions) · HP Z2 Tower G8 Workstation (△ Fits with conditions) · HP Z2 Tower G9 Workstation (△ Fits with conditions) · Lenovo ThinkCentre M90t (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 3 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 4 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 5 (△ Fits with conditions) · Lenovo ThinkCentre M910 Tower (△ Fits with conditions)
- GeForce RTX 5060 Ti (Reference design), 16 GB — ✓ Fits in VRAM Estimated Dell OptiPlex 7000 Tower (2022) (△ Fits with conditions) · Dell OptiPlex 7080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 7090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex Tower Plus 7010 (2023) (△ Fits with conditions) · Dell Precision 3630 Tower (△ Fits with conditions) · Dell Precision 3660 Tower (△ Fits with conditions) · Dell Precision 3680 Tower (△ Fits with conditions) · HP Elite Tower 600 G9 (△ Fits with conditions) · HP Pro Tower 400 G9 (△ Fits with conditions) · HP Z2 Tower G5 Workstation (△ Fits with conditions) · HP Z2 Tower G8 Workstation (△ Fits with conditions) · Lenovo ThinkCentre M70t Gen 4 (△ Fits with conditions) · Lenovo ThinkCentre M70t Gen 5 (△ Fits with conditions) · Lenovo ThinkCentre M80t Gen 3 (△ Fits with conditions) · Lenovo ThinkCentre M90t (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 3 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 4 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 5 (△ Fits with conditions) · Lenovo ThinkCentre M910 Tower (△ Fits with conditions)
- NVIDIA Quadro P5000 (Reference design) — ✓ Fits in VRAM Estimated Dell OptiPlex 7000 Tower (2022) (△ Fits with conditions) · Dell OptiPlex 7080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 7090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex Tower Plus 7010 (2023) (△ Fits with conditions) · Dell Precision 3630 Tower (△ Fits with conditions) · Dell Precision 3680 Tower (△ Fits with conditions) · HP Elite Tower 600 G9 (△ Fits with conditions) · HP Pro Tower 400 G9 (△ Fits with conditions) · HP Z2 Tower G5 Workstation (△ Fits with conditions) · HP Z2 Tower G8 Workstation (△ Fits with conditions) · HP Z2 Tower G9 Workstation (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 3 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 4 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 5 (△ Fits with conditions) · Lenovo ThinkCentre M910 Tower (△ Fits with conditions)
- NVIDIA RTX 2000 Ada Generation — ✓ Fits in VRAM Estimated Dell OptiPlex 3050 Small Form Factor (2017) (△ Fits with conditions) · Dell OptiPlex 3050 Tower (2017) (△ Fits with conditions) · Dell OptiPlex 3060 Small Form Factor (2018) (△ Fits with conditions) · Dell OptiPlex 3060 Tower (2018) (△ Fits with conditions) · Dell OptiPlex 3080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 3090 Small Form Factor (2021) (△ Fits with conditions) · Dell OptiPlex 3090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex 5040 Mini Tower (2015) (△ Fits with conditions) · Dell OptiPlex 5040 Small Form Factor (2015) (△ Fits with conditions) · Dell OptiPlex 5050 Small Form Factor (2017) (△ Fits with conditions) · Dell OptiPlex 5050 Tower (2017) (△ Fits with conditions) · Dell OptiPlex 5060 Small Form Factor (2018) (△ Fits with conditions) · Dell OptiPlex 5060 Tower (2018) (△ Fits with conditions) · Dell OptiPlex 5070 Small Form Factor (2019) (△ Fits with conditions) · Dell OptiPlex 5070 Tower (2019) (△ Fits with conditions) · Dell OptiPlex 5080 Small Form Factor (2020) (△ Fits with conditions) · Dell OptiPlex 5080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 5090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex 7000 Small Form Factor (2022) (△ Fits with conditions) · Dell OptiPlex 7000 Tower (2022) (△ Fits with conditions) · Dell OptiPlex 7040 Mini Tower (2015) (△ Fits with conditions) · Dell OptiPlex 7040 Small Form Factor (2015) (△ Fits with conditions) · Dell OptiPlex 7050 Small Form Factor (2017) (△ Fits with conditions) · Dell OptiPlex 7050 Tower (2017) (△ Fits with conditions) · Dell OptiPlex 7060 Small Form Factor (2018) (△ Fits with conditions) · Dell OptiPlex 7060 Tower (2018) (△ Fits with conditions) · Dell OptiPlex 7070 Small Form Factor (2019) (△ Fits with conditions) · Dell OptiPlex 7070 Tower (2019) (△ Fits with conditions) · Dell OptiPlex 7080 Small Form Factor (2020) (△ Fits with conditions) · Dell OptiPlex 7080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 7090 Small Form Factor (2021) (△ Fits with conditions) · Dell OptiPlex 7090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex Small Form Factor 7010 (2023) (△ Fits with conditions) · Dell OptiPlex Small Form Factor Plus 7010 (2023) (△ Fits with conditions) · Dell OptiPlex Tower 7010 (2023) (△ Fits with conditions) · Dell OptiPlex Tower Plus 7010 (2023) (△ Fits with conditions) · Dell Precision 3630 Tower (△ Fits with conditions) · Dell Precision 3660 Tower (△ Fits with conditions) · Dell Precision 3680 Tower (△ Fits with conditions) · Dell Precision 5820 Tower (△ Fits with conditions) · HP Elite Tower 600 G9 (△ Fits with conditions) · HP Elite Tower 800 G9 (✓ Fits) · HP Pro Tower 400 G9 (△ Fits with conditions) · HP Z2 Small Form Factor G8 Workstation (△ Fits with conditions) · HP Z2 Tower G5 Workstation (△ Fits with conditions) · HP Z2 Tower G8 Workstation (△ Fits with conditions) · HP Z2 Tower G9 Workstation (△ Fits with conditions) · Lenovo ThinkCentre M70t (△ Fits with conditions) · Lenovo ThinkCentre M70t Gen 4 (△ Fits with conditions) · Lenovo ThinkCentre M70t Gen 5 (△ Fits with conditions) · Lenovo ThinkCentre M710 Tower (△ Fits with conditions) · Lenovo ThinkCentre M720 Tower (△ Fits with conditions) · Lenovo ThinkCentre M75t Gen 5 (△ Fits with conditions) · Lenovo ThinkCentre M80t (△ Fits with conditions) · Lenovo ThinkCentre M80t Gen 3 (✓ Fits) · Lenovo ThinkCentre M90t (✓ Fits) · Lenovo ThinkCentre M90t Gen 3 (✓ Fits) · Lenovo ThinkCentre M90t Gen 4 (✓ Fits) · Lenovo ThinkCentre M90t Gen 5 (✓ Fits) · Lenovo ThinkCentre M910 Tower (△ Fits with conditions) · Lenovo ThinkCentre M920 Tower (△ Fits with conditions) · Lenovo ThinkCentre neo 50t Gen 4 (△ Fits with conditions)
- NVIDIA RTX A4000 — ✓ Fits in VRAM Estimated Dell OptiPlex 7000 Tower (2022) (△ Fits with conditions) · Dell OptiPlex 7060 Tower (2018) (△ Fits with conditions) · Dell OptiPlex 7070 Tower (2019) (△ Fits with conditions) · Dell OptiPlex 7080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 7090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex Tower Plus 7010 (2023) (△ Fits with conditions) · Dell Precision 3630 Tower (△ Fits with conditions) · Dell Precision 3660 Tower (△ Fits with conditions) · Dell Precision 3680 Tower (△ Fits with conditions) · HP Elite Tower 600 G9 (△ Fits with conditions) · HP Pro Tower 400 G9 (△ Fits with conditions) · HP Z2 Tower G5 Workstation (△ Fits with conditions) · HP Z2 Tower G8 Workstation (△ Fits with conditions) · HP Z2 Tower G9 Workstation (△ Fits with conditions) · Lenovo ThinkCentre M90t (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 3 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 4 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 5 (△ Fits with conditions) · Lenovo ThinkCentre M910 Tower (△ Fits with conditions) · Lenovo ThinkCentre M920 Tower (△ Fits with conditions)
- GeForce RTX 2060 12GB (Reference design) — △ Fits at short context only Estimated Dell OptiPlex 7000 Tower (2022) (△ Fits with conditions) · Dell OptiPlex 7080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 7090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex Tower Plus 7010 (2023) (△ Fits with conditions) · Dell Precision 3630 Tower (△ Fits with conditions) · Dell Precision 3680 Tower (△ Fits with conditions) · HP Elite Tower 600 G9 (△ Fits with conditions) · HP Pro Tower 400 G9 (△ Fits with conditions) · HP Z2 Tower G5 Workstation (△ Fits with conditions) · HP Z2 Tower G8 Workstation (△ Fits with conditions) · HP Z2 Tower G9 Workstation (△ Fits with conditions) · Lenovo ThinkCentre M70t Gen 4 (△ Fits with conditions) · Lenovo ThinkCentre M70t Gen 5 (△ Fits with conditions) · Lenovo ThinkCentre M80t Gen 3 (△ Fits with conditions) · Lenovo ThinkCentre M90t (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 3 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 4 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 5 (△ Fits with conditions) · Lenovo ThinkCentre M910 Tower (△ Fits with conditions)
- Intel Arc B580 (Reference design) — △ Fits at short context only Estimated Dell OptiPlex 7000 Tower (2022) (△ Fits with conditions) · Dell OptiPlex 7080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 7090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex Tower Plus 7010 (2023) (△ Fits with conditions) · Dell Precision 3630 Tower (△ Fits with conditions) · Dell Precision 3680 Tower (△ Fits with conditions) · HP Elite Tower 600 G9 (△ Fits with conditions) · HP Pro Tower 400 G9 (△ Fits with conditions) · HP Z2 Tower G5 Workstation (△ Fits with conditions) · HP Z2 Tower G8 Workstation (△ Fits with conditions) · HP Z2 Tower G9 Workstation (△ Fits with conditions)
- NVIDIA Quadro M6000 (Reference design) — △ Fits at short context only Estimated Dell OptiPlex 7000 Tower (2022) (△ Fits with conditions) · Dell OptiPlex 7080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 7090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex Tower Plus 7010 (2023) (△ Fits with conditions) · Dell Precision 3630 Tower (△ Fits with conditions) · Dell Precision 3680 Tower (△ Fits with conditions) · HP Z2 Tower G5 Workstation (△ Fits with conditions) · HP Z2 Tower G8 Workstation (△ Fits with conditions) · HP Z2 Tower G9 Workstation (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 3 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 4 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 5 (△ Fits with conditions)
- NVIDIA RTX 3080TI — △ Fits at short context only Estimated Dell Precision 3660 Tower (✓ Fits)
- NVIDIA RTX A2000 12GB — △ Fits at short context only Estimated Dell OptiPlex 3050 Small Form Factor (2017) (△ Fits with conditions) · Dell OptiPlex 3050 Tower (2017) (△ Fits with conditions) · Dell OptiPlex 3060 Small Form Factor (2018) (△ Fits with conditions) · Dell OptiPlex 3060 Tower (2018) (△ Fits with conditions) · Dell OptiPlex 3080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 3090 Small Form Factor (2021) (△ Fits with conditions) · Dell OptiPlex 3090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex 5040 Mini Tower (2015) (△ Fits with conditions) · Dell OptiPlex 5040 Small Form Factor (2015) (△ Fits with conditions) · Dell OptiPlex 5050 Small Form Factor (2017) (△ Fits with conditions) · Dell OptiPlex 5050 Tower (2017) (△ Fits with conditions) · Dell OptiPlex 5060 Small Form Factor (2018) (△ Fits with conditions) · Dell OptiPlex 5060 Tower (2018) (△ Fits with conditions) · Dell OptiPlex 5070 Small Form Factor (2019) (△ Fits with conditions) · Dell OptiPlex 5070 Tower (2019) (△ Fits with conditions) · Dell OptiPlex 5080 Small Form Factor (2020) (△ Fits with conditions) · Dell OptiPlex 5080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 5090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex 7000 Small Form Factor (2022) (△ Fits with conditions) · Dell OptiPlex 7000 Tower (2022) (△ Fits with conditions) · Dell OptiPlex 7040 Mini Tower (2015) (△ Fits with conditions) · Dell OptiPlex 7040 Small Form Factor (2015) (△ Fits with conditions) · Dell OptiPlex 7050 Small Form Factor (2017) (△ Fits with conditions) · Dell OptiPlex 7050 Tower (2017) (△ Fits with conditions) · Dell OptiPlex 7060 Small Form Factor (2018) (△ Fits with conditions) · Dell OptiPlex 7060 Tower (2018) (△ Fits with conditions) · Dell OptiPlex 7070 Small Form Factor (2019) (△ Fits with conditions) · Dell OptiPlex 7070 Tower (2019) (△ Fits with conditions) · Dell OptiPlex 7080 Small Form Factor (2020) (△ Fits with conditions) · Dell OptiPlex 7080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 7090 Small Form Factor (2021) (△ Fits with conditions) · Dell OptiPlex 7090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex Small Form Factor 7010 (2023) (△ Fits with conditions) · Dell OptiPlex Small Form Factor Plus 7010 (2023) (△ Fits with conditions) · Dell OptiPlex Tower 7010 (2023) (△ Fits with conditions) · Dell OptiPlex Tower Plus 7010 (2023) (△ Fits with conditions) · Dell Precision 3630 Tower (△ Fits with conditions) · Dell Precision 3660 Tower (△ Fits with conditions) · Dell Precision 3680 Tower (△ Fits with conditions) · Dell Precision 5820 Tower (△ Fits with conditions) · HP Elite Tower 600 G9 (△ Fits with conditions) · HP Elite Tower 800 G9 (✓ Fits) · HP Pro Tower 400 G9 (△ Fits with conditions) · HP Z2 Small Form Factor G8 Workstation (△ Fits with conditions) · HP Z2 Tower G5 Workstation (△ Fits with conditions) · HP Z2 Tower G8 Workstation (△ Fits with conditions) · HP Z2 Tower G9 Workstation (△ Fits with conditions) · Lenovo ThinkCentre M70t (△ Fits with conditions) · Lenovo ThinkCentre M70t Gen 4 (△ Fits with conditions) · Lenovo ThinkCentre M70t Gen 5 (△ Fits with conditions) · Lenovo ThinkCentre M710 Tower (△ Fits with conditions) · Lenovo ThinkCentre M720 Tower (△ Fits with conditions) · Lenovo ThinkCentre M75t Gen 5 (△ Fits with conditions) · Lenovo ThinkCentre M80t (△ Fits with conditions) · Lenovo ThinkCentre M80t Gen 3 (✓ Fits) · Lenovo ThinkCentre M90t (✓ Fits) · Lenovo ThinkCentre M90t Gen 3 (✓ Fits) · Lenovo ThinkCentre M90t Gen 4 (✓ Fits) · Lenovo ThinkCentre M90t Gen 5 (✓ Fits) · Lenovo ThinkCentre M910 Tower (△ Fits with conditions) · Lenovo ThinkCentre M920 Tower (△ Fits with conditions) · Lenovo ThinkCentre neo 50t Gen 4 (△ Fits with conditions)
- PALIT GeForce RTX 3060 Infinity 2 OC — △ Fits at short context only Estimated Dell OptiPlex 7000 Tower (2022) (△ Fits with conditions) · Dell OptiPlex 7080 Tower (2020) (△ Fits with conditions) · Dell OptiPlex 7090 Tower (2021) (△ Fits with conditions) · Dell OptiPlex Tower Plus 7010 (2023) (△ Fits with conditions) · Dell Precision 3630 Tower (△ Fits with conditions) · Dell Precision 3660 Tower (△ Fits with conditions) · Dell Precision 3680 Tower (△ Fits with conditions) · HP Elite Tower 600 G9 (△ Fits with conditions) · HP Pro Tower 400 G9 (△ Fits with conditions) · HP Z2 Tower G5 Workstation (△ Fits with conditions) · HP Z2 Tower G8 Workstation (△ Fits with conditions) · HP Z2 Tower G9 Workstation (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 3 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 4 (△ Fits with conditions) · Lenovo ThinkCentre M90t Gen 5 (△ Fits with conditions) · Lenovo ThinkCentre M910 Tower (△ Fits with conditions)
Verify with the manufacturer before purchasing.
Sources
| Document | Publisher | Kind | Read on |
|---|---|---|---|
| Unsloth phi-4-GGUF distribution repository (file listing and actual file sizes) | Hugging Face (model distribution) | supporting | 2026-09-24 |
| Microsoft official phi-4-gguf distribution repository (confirming that no file labelled Q4_K_M is distributed there; only Q4_0, Q4_1, Q4_K, Q4_K_S, IQ4_NL and IQ4_XS) | Hugging Face (model distribution) | primary | 2026-09-24 |
| Microsoft official phi-4 config.json (num_hidden_layers=40, num_key_value_heads=10, hidden_size 5120 divided by num_attention_heads 40 = head_dim 128, sliding_window=null) | Hugging Face (model distribution) | primary | 2026-09-24 |
| Microsoft official Phi-4 model card | Hugging Face (model distribution) | primary | — |