on

Can the Apple M5 Pro (48 GB) run Aya Vision 32B?

50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs well

Runs well. At Q3_K_M it needs about 21.1 GB of 36.0 GB usable, with an estimated speed of 12.7 tok/s.

Best quant
Q3_K_M
Generation speed
12.7 tok/s
Prompt processing
176 tok/s
First token (1K prompt)
5.8 s
Largest safe context
16K

Best app to run it on the Apple M5 Pro (48 GB)

On macOS

LM Studio

Desktop app · runs on llama.cpp, MLX · use the MLX build

  • Runs the MLX build, typically up to 10% faster than GGUF for a model with 33.1B active parameters on Apple silicon.
  • Point-and-click: search, download and chat in one window.

Open Aya Vision 32B in LM Studio

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

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 50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at Q3_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 well
How well it runs on the Apple M5 Pro (48 GB): 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.22.7 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.8.4 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.13.5 / 15
Match score69.6 / 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 Apple M5 Pro (48 GB)

Quant Memory needed Available Speed Runs Quality Download
Q2_K 18.1 GB 36.0 GB 16.1 tok/s Runs well 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q3_K_M 21.1 GB 36.0 GB 12.7 tok/s Runs well 50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q4_K_M 25.0 GB 36.0 GB 9.8 tok/s Slow 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. All files (opens in a new tab)
Q5_K_M 28.4 GB 36.0 GB 8.1 tok/s Slow 58Good quality (B) · 58 of 100: how capable the model is at Q5_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)
Q6_K 32.0 GB 36.0 GB 6.8 tok/s Slowtight fit 59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q8_0 40.0 GB 36.0 GB 4.2 tok/s Slowfar over GPU memory limit 60Good quality (B) · 60 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
F16 71.1 GB 36.0 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 M5 Pro 48GB?

At Q3_K_M it needs about 21.1 GB. The M5 Pro 48GB has 36.0 GB usable.

How fast is Aya Vision 32B on the M5 Pro 48GB?

About 12.7 tok/s at Q3_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 M5 Pro 48GB?

Q3_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?