on

Can the NVIDIA L40S run Aya Vision 32B?

57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs great

Runs great. At Q4_K_M it needs about 24.6 GB of 48.0 GB usable, with an estimated speed of 32.0 tok/s.

Best quant
Q4_K_M
Generation speed
32.0 tok/s
Prompt processing
1,990 tok/s
First token (1K prompt)
0.5 s
Largest safe context
16K

Best app to run it on the NVIDIA L40S

On Linux

vLLM

Inference server · runs on vLLM

  • The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.
vllm serve CohereLabs/aya-vision-32b
  • SGLang The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.
  • Docker Model Runner Handy if you already work in Docker.

On Windows

vLLM

Inference server · runs on vLLM

  • The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.
  • On Windows it runs through WSL2.
vllm serve CohereLabs/aya-vision-32b
  • SGLang The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.
  • Docker Model Runner Handy if you already work in Docker.

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

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 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at Q4_K_M, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs great
How well it runs on the NVIDIA L40S: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

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 memory; fewer when part spills to system RAM.25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.13.4 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.11.8 / 15
Match score75.9 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the NVIDIA L40S

Quant Memory needed Available Speed Runs Quality Download
Q2_K 17.6 GB 48.0 GB 52.6 tok/s Runs great 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q3_K_M 20.6 GB 48.0 GB 41.4 tok/s Runs great 50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q4_K_M 24.6 GB 48.0 GB 32.0 tok/s Runs great 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q5_K_M 27.9 GB 48.0 GB 26.4 tok/s Runs well 58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q6_K 31.5 GB 48.0 GB 22.2 tok/s Runs well 59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q8_0 39.5 GB 48.0 GB 16.3 tok/s Runs well 60Good quality (B) · 60 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
F16 70.6 GB 48.0 GB — Won't run 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. 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

Quick answers

How much memory does Aya Vision 32B need on the NVIDIA L40S 48GB?

At Q4_K_M it needs about 24.6 GB. The NVIDIA L40S 48GB has 48.0 GB usable.

How fast is Aya Vision 32B on the NVIDIA L40S 48GB?

About 32.0 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Aya Vision 32B should I use on the NVIDIA L40S 48GB?

Q4_K_M. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

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.

Was this page helpful?