VRAM TableGPU fit and local-LLM VRAM for OEM desktops, from published specifications Search by model
Browse categories

NVIDIA Tesla P4

NVIDIA (specification common to board partners) · 8 GB · catalogue identifier tesla-p4-8gb · last updated 2026-09-24

82 desktops in this database carry a verdict for the NVIDIA Tesla P4: 18 do not fit (all estimates) and 64 are unverified. Estimated Of the 18 desktops it does not fit, all 18 conflict with the desktop's maximum card length; the Lenovo ThinkCentre M70s is one of the 18. Estimated Among the 43 cards with 8 GB in this database, its board power of 75 W is within 50–295 W, with 1 lower and 41 higher; its length of 167.64 mm compares with 163–275 mm where published. Estimated The largest listed model its 8 GB holds at 32k context is Qwen3 4B (Q4_K_M, needs 7.9 GiB). Estimated

Published specifications for this card, the OEM desktops whose own specifications accept it, and how much of a local language model its memory holds.

We have not physically tested this combination. Data is compiled from official specification sheets and cited sources.

Specifications

Graphics processor
NVIDIA Tesla P4 (PCIe)
Board
NVIDIA Tesla P4 (NVIDIA (specification common to board partners))
Card memory
8 GB · E Source for this figure not recorded per field; see record sources
Total board power
75 W · D read 2026-09-19 [S1]
Vendor's recommended system power
Not stated by the cited specification
Auxiliary power connector
Not required · D read 2026-09-19 [S1]
Length
167.64 mm · D read 2026-09-19 [S1]
Height
68.58 mm
Width
Not stated by the cited specification
Slot widths occupied
1 · D read 2026-09-19 [S1]
Low profile
Yes · A read 2026-09-19 [S2]
CUDA
Yes

Each graded figure above cites: [S1] Tesla P4 GPU Accelerator Product Brief (PB-08449-001_v01, NVIDIA, Wayback Machine capture); [S2] NVIDIA Tesla P4 (PCIe) specifications (official).

Power. Leave headroom; OEM PSUs are often rated at the limit. The recommended system figure above is the card vendor's own, and it assumes a retail supply rather than an OEM one.

Desktops that take this card

No desktop in this database carries a fitting verdict for this card. It was assessed against 82 of them. Its published figures are inside the range that other cards clear here, so the conflict is with particular machines rather than with every one of them; each desktop's own page says what its specifications record.

This card has been assessed against 82 desktops in this database. Each verdict is a statement about published specifications, not about a tested combination.

  • ✓ Fits: 0
  • △ Fits with conditions: 0
  • ✕ Does not fit: 18 (all estimates) Estimated
  • ? Unverified: 64

✕ Does not fit 18 desktops, grouped by the published limit that conflicts with this card's published figures:

? Unverified 64 desktops. The evidence does not settle these either way, which is not the same as them being ruled out.

Verify with the manufacturer before purchasing.

What each verdict means. Every one of them is a statement about published specifications.
VerdictMeaning
✓ Fits Published specifications show no physical or electrical conflict.
△ Fits with conditions Published specifications allow it only under the stated conditions.
✕ Does not fit Published specifications rule the combination out: the card needs a connector the machine does not have, draws more than the supply provides, or is physically too large. It is a statement about specifications, not a report of a failed attempt.
? Unverified There is not enough evidence to say.

A dashed Estimated badge at the start of a line marks every verdict on that line as published as an estimate, and the grade beside it applies to each of them. The document behind each verdict, and the desktop's own figures, are listed on the desktop's own page. This card has a verdict for 82 of the 82 desktops in this database; the remaining 0 have not been assessed against it, which is not the same as them being ruled out.

Local language models this card's memory holds

Arithmetic shared by the models below. Sentences that read the same for more than one model are stated once here; each row names the ones it carries by number.

  1. 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. (6 rows)
Calculated from the published file size and the model architecture.
ModelOutcome Needs at 32k contextThe arithmetic Confidence
Qwen3 4B Q4_K_M ✓ Fits in VRAM Estimated 7.9 GiB 8 GB of memory is at least the 7.9 GB required at a context length of 32,768 tokens. [1] BE
Qwen3 1.7B Q4_K_M ✓ Fits in VRAM Estimated 5.6 GiB 8 GB of memory is at least the 5.6 GB required at a context length of 32,768 tokens. [1] BE
Qwen3 0.6B Q4_K_M ✓ Fits in VRAM Estimated 4.9 GiB 8 GB of memory is at least the 4.9 GB required at a context length of 32,768 tokens. [1] BE
Gemma 3 4B Q4_0 (QAT) ✓ Fits in VRAM Estimated 4.7 GiB 8 GB of memory is at least the 4.7 GB required at a context length of 32,768 tokens. [1] BE
Qwen3 8B Q4_K_M △ Fits at short context only Estimated 10.2 GiB 8 GB of memory covers the 6.3 GB required at a context length of 4,096 tokens, but not the 10.2 GB required at 32,768 tokens. [1] BE
Llama 3.1 8B Q4_K_M △ Fits at short context only Estimated 9.6 GiB 8 GB of memory covers the 6.1 GB required at a context length of 4,096 tokens, but not the 9.6 GB required at 32,768 tokens. [1] BE

✕ Exceeds VRAM 12 models need more memory at 32k context than this card has, 12 of them published as an estimate. The arithmetic for each is on the model's own page.

Exceeds VRAM does not mean the model will not run: inference software can keep part of a model in system memory. How fast that is, and whether it is pleasant to use, is outside what this site measures. The sizing rule and its constants are on the Methodology page.

Cards whose published memory size is the same, so the local-model outcomes on this page apply to them as well. Whether a given desktop accepts them is a separate question, answered on each card's own page.

Sources

Every document this page draws on, with the date it was read.
DocumentPublisherKindRead on
NVIDIA Tesla P4 (PCIe) specifications (official) NVIDIA Manufacturer official documentation 2026-09-19
Tesla P4 GPU Accelerator Product Brief (PB-08449-001_v01, NVIDIA, Wayback Machine capture) web.archive.org primary 2026-09-19

We have not physically tested this combination. Data is compiled from official specification sheets and cited sources. Verify with the manufacturer before purchasing.