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

GeForce GTX 1660 Discrete [gtx-1660-super-6gb]

Factory graphics option · catalogue identifier gtx-1660-super-6gb · last updated 2026-09-24

1 desktop in this database carries a verdict for the GeForce GTX 1660 Discrete [gtx-1660-super-6gb]: 1 fits. Fits without conditions: the Lenovo ThinkCentre M90t.

This is a factory option, not a card you can buy. A computer manufacturer lists it in its own specification sheet for a machine, exactly as “GeForce GTX 1660 Discrete”. The published specifications therefore record a card of this class as a factory option for that machine, but no card-level specification is published for the option itself, so this page carries no dimensions, no board power, no connector, and no purchase link.

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

About the name. The upstream identifier says "Super, 6GB", but the cited specification sheet lists the option as "GeForce GTX 1660 Discrete" with neither the Super suffix nor a memory size. The name shown is the one the sheet states.

Another entry in this database carries the same printed name. The two are distinguished here by catalogue identifier.

Desktops whose verdicts reference this option

This card has been assessed against 1 desktop in this database. Each verdict is a statement about published specifications, not about a tested combination.

  • ✓ Fits: 1
  • △ Fits with conditions: 0
  • ✕ Does not fit: 0
  • ? Unverified: 0

✓ Fits 1 desktop:

  • confidence A (1): Lenovo ThinkCentre M90t (The manufacturer offers this card as a factory configuration for this model, so the chassis, the bracket and the supply are established by that shipping fact — for this model alone. The manufacturer's specification sheet gives no dimensions and no power draw for the card on its own, so the coverage requirement does not apply to it.)

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 1 of the 82 desktops in this database; the remaining 81 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. The memory size of this graphics option is not stated in the cited specification, so no verdict is given. (18 rows)
  2. 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. (8 rows)
Calculated from the published file size and the model architecture.
ModelOutcome Needs at 32k contextThe arithmetic Confidence
GLM-4.5-Air Q4_K_M ? Unverified 74.8 GiB [1] [2] BD
GPT-OSS 120B MXFP4 (the vendor's own native quantisation) ? Unverified 62.9 GiB [1] B
Llama 3.1 70B Q4_K_M ? Unverified 50.7 GiB [1] [2] BD
Qwen3 32B Q4_K_M ? Unverified 27.5 GiB [1] B
EXAONE 4.0 32B Q4_K_M ? Unverified 21.8 GiB [1] B
Qwen3 30B-A3B Instruct 2507 Q4_K_M ? Unverified 21.3 GiB [1] [2] BD
Gemma 3 27B Q4_0 (QAT) ? Unverified 20.0 GiB [1] B
Mistral Small 3.2 24B Instruct Q4_K_M ? Unverified 19.4 GiB [1] [2] BD
Phi-4 14B Q4_K_M ? Unverified 15.6 GiB [1] [2] BD
GPT-OSS 20B MXFP4 (the vendor's own native quantisation) ? Unverified 14.6 GiB [1] B
Qwen3 14B Q4_K_M ? Unverified 14.4 GiB [1] B
Gemma 3 12B Q4_0 (QAT) ? Unverified 10.9 GiB [1] B
Qwen3 8B Q4_K_M ? Unverified 10.2 GiB [1] B
Llama 3.1 8B Q4_K_M ? Unverified 9.6 GiB [1] [2] BD
Qwen3 4B Q4_K_M ? Unverified 7.9 GiB [1] B
Qwen3 1.7B Q4_K_M ? Unverified 5.6 GiB [1] [2] BD
Qwen3 0.6B Q4_K_M ? Unverified 4.9 GiB [1] [2] BD
Gemma 3 4B Q4_0 (QAT) ? Unverified 4.7 GiB [1] B

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.

Sources

Every document this page draws on, with the date it was read.
DocumentPublisherKindRead on
ThinkCentre M90t Platform Specifications PSREF (September 25 2023 revision) Lenovo primary 2026-09-22

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