LLMs ·

Aya Vision 32B

Parameters
33B
Architecture
Dense
Max context
16K tokens
License
cc-by-nc-4.0
Released
2025-03

How to run it

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.

Apps that run Aya Vision 32B

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

LM Studio

Runs the MLX build, typically up to 10% faster than GGUF for a model with 33.1B active parameters on Apple silicon.

Also good:

Windows PC, NVIDIA GPU

Docker Model Runner

Handy if you already work in Docker.

Also good:

Windows PC, AMD Radeon

Docker Model Runner

Handy if you already work in Docker.

Also good:

Linux, NVIDIA GPU

Docker Model Runner

Handy if you already work in Docker.

Also good:

Linux server, 80 GB+ GPUs

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.

Also good:

App Type Opens it as Systems Engine Start
LM Studio Desktop app MLX macOSWindowsLinux llama.cpp, MLX Open in LM Studio
Jan Desktop app MLX macOSWindowsLinux llama.cpp, MLX Get Jan
MLX LM CLI + API MLX macOS MLX 
mlx_lm.chat --model mlx-community/aya-vision-32b-4bit
vLLM Server Original weights WSLWindowsLinux vLLM 
vllm serve CohereLabs/aya-vision-32b
SGLang Server Original weights WSLWindowsLinux SGLang 
python3 -m sglang.launch_server --model-path CohereLabs/aya-vision-32b
Docker Model Runner CLI + API Original weights macOSWindowsLinux llama.cpp, vLLM 
docker model run hf.co/CohereLabs/aya-vision-32b
Unsloth Desktop Desktop app MLX macOSWindowsLinux llama.cpp, MLX, stable-diffusion.cpp Get Unsloth Desktop
Atomic Chat Desktop app MLX macOSWindowsLinux llama.cpp, MLX-VLM Open in Atomic Chat
Text Generation WebUI Desktop app Original weights macOSWindowsLinux llama.cpp, Transformers, ExLlamaV3 Get Text Generation WebUI
Msty Studio Desktop app MLX macOSWindowsLinux Ollama, llama.cpp, MLX Get Msty Studio
Inferencer Desktop app MLX macOS MLX Get Inferencer
exo Server MLX macOSLinux MLX Get exo

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps. Try another context length.

Quantization Quality Weights Total at 8K context Total at 16K context Download
Q2_K Low 13.3 GB 15.2 GB 16.5 GB All files (opens in a new tab)
Q3_K_M Low 16.2 GB 18.2 GB 19.5 GB All files (opens in a new tab)
Q4_K_M Good 20.2 GB 22.2 GB 23.5 GB All files (opens in a new tab)
Q5_K_M High 23.5 GB 25.5 GB 26.8 GB All files (opens in a new tab)
Q6_K High 27.2 GB 29.1 GB 30.5 GB All files (opens in a new tab)
Q8_0 Very high 35.1 GB 37.1 GB 38.4 GB All files (opens in a new tab)
F16 Full 66.3 GB 68.2 GB 69.6 GB Original weights (opens in a new tab)

Best hardware for Aya Vision 32B

The least expensive GPU in our catalog that runs it without offloading is the AMD Radeon RX 7600 XT (launch price $329) at Q2_K.

Quality Hardware Quant Memory Speed Runs
58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Founders EditionNVIDIA GeForce RTX 5090 Q5_K_M 27.1 GB / 32.0 GB 54.8 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 79/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Founders EditionNVIDIA GeForce RTX 4090 Q4_K_M 23.4 GB / 24.0 GB 37.3 tok/s Runs welltight fit
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. ASUS ROG Strix GeForce RTX 3090 OC Edition 24GB GDDR6XNVIDIA GeForce RTX 3090 Q4_K_M 23.4 GB / 24.0 GB 34.7 tok/s Runs welltight fit
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Sapphire NITRO+ AMD Radeon RX 7900 XTX Vapor-X 24GBAMD Radeon RX 7900 XTX Q4_K_M 23.4 GB / 24.0 GB 30.6 tok/s Runs welltight fit
59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Workstation EditionNVIDIA RTX PRO 6000 Blackwell Q6_K 33.9 GB / 96.0 GB 46.1 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 73/100 (quality, fit, speed and memory use) sets the ranking. Apple MacBook Pro (14-inch, M4 Pro or M4 Max, 2024)Apple M4 Max (64 GB) Q4_K_M 26.0 GB / 48.0 GB 17.4 tok/s Runs well
42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPERNVIDIA GeForce RTX 4070 Ti SUPER Q2_K 16.0 GB / 16.0 GB 40.9 tok/s Runs welltight fit
42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPERNVIDIA GeForce RTX 4080 SUPER Q2_K 16.0 GB / 16.0 GB 44.8 tok/s Runs welltight fit
42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. ASUS TUF Gaming GeForce RTX 5070 Ti 16GB GDDR7 OC EditionNVIDIA GeForce RTX 5070 Ti Q2_K 16.0 GB / 16.0 GB 54.5 tok/s Runs welltight fit
42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 Founders EditionNVIDIA GeForce RTX 5080 Q2_K 16.0 GB / 16.0 GB 58.4 tok/s Runs welltight fit

Check it on your own hardware

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?