Check my GPU

on

Can the NVIDIA GeForce RTX 4090 run Aya Vision 32B?

79 ptsGreat (A) · 79 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 14.5/15, Memory use 15.0/15

Yes, with little memory to spare

Tight fit. At Q4_K_M it needs about 23.4 GB of 24.0 GB usable, with an estimated speed of 37.3 tok/s.

Best quant
Q4_K_M
Generation speed
37.3 tok/s
Prompt processing
1,795 tok/s
First token (1K prompt)
0.6 s
Largest safe context
11K

Download Aya Vision 32B

Original weights · Hugging Face

Full-precision files from Cohere, for fine-tuning, vLLM, Transformers.

huggingface.co/CohereLabs/aya-vision-32b (opens in a new tab)

Free Hugging Face account needed: accept the license on the model page and the download starts right away.

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

How the A grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.25.7 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.24.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.14.5 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.15.0 / 15
Total79.1 / 10079 ptsGreat (A) · 79 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 14.5/15, Memory use 15.0/15

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every quantization on the NVIDIA GeForce RTX 4090

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 16.4 GB 24.0 GB 61.3 tok/s Runs well 73 ptsGreat (A) · 73 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 All files (opens in a new tab)
Q3_K_M 19.4 GB 24.0 GB 48.3 tok/s Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 22.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 All files (opens in a new tab)
Q4_K_M 23.4 GB 24.0 GB 37.3 tok/s Tight fit 79 ptsGreat (A) · 79 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 14.5/15, Memory use 15.0/15 All files (opens in a new tab)
Q5_K_M 26.7 GB 24.0 GB 11.8 tok/s Runs with offload 59 ptsGood (B) · 59 of 100 points: Model quality 26.2/45, Memory fit 10.0/25, Speed 8.2/15, Memory use 15.0/15 All files (opens in a new tab)
Q6_K 30.3 GB 24.0 GB 6.0 tok/s Runs with offload 57 ptsUsable (C) · 57 of 100 points: Model quality 26.7/45, Memory fit 10.0/25, Speed 5.8/15, Memory use 15.0/15 All files (opens in a new tab)
Q8_0 38.3 GB 24.0 GB 2.8 tok/s Heavy offload 49 ptsUsable (C) · 49 of 100 points: Model quality 27.0/45, Memory fit 4.0/25, Speed 4.0/15, Memory use 15.0/15 All files (opens in a new tab)
F16 69.4 GB 24.0 GB — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.