Mistral Small 3.2 24B on Apple M3 Ultra (512 GB)

Can the Apple M3 Ultra (512 GB) run Mistral Small 3.2 24B?

Yes, it runs great

Runs great. At Q4_K_M it needs about 47.3 GB of 384 GB usable, with an estimated speed of 36.1 tok/s.

Best quant: Q4_K_M
Generation speed: 36.1 tok/s
Prompt processing: 733 tok/s
First token (1K prompt): 1.4 s
Largest safe context: 128K

Best app to run it on the Apple M3 Ultra (512 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 24B active parameters on Apple silicon.
Point-and-click: search, download and chat in one window.

Open Mistral Small 3.2 24B in LM Studio

Ollama One command with Ollama’s own build of this model.
llama.cpp Usually the first to support new model architectures.

Want an agent? Mistral Small 3.2 24B supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

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 Mistral Small 3.2 24B

Recommended for the Apple M3 Ultra (512 GB): Q4_K_M. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run mistral-small3.2:24b-instruct-2506-q4_K_M

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q4_K_M file (opens in a new tab)

huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q4_K_M

Original weights · Hugging Face

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

huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Mistral AI. The weights themselves download from Hugging Face.

github.com/mistralai/mistral-inference (opens in a new tab)

Mistral AI’s official inference code.

git clone https://github.com/mistralai/mistral-inference

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (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 Apple M3 Ultra (512 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.	29.1 / 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.	14.2 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	2.8 / 15
Match score	71.2 / 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 M3 Ultra (512 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	42.3 GB	384 GB	59.2 tok/s	Runs great	47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	44.4 GB	384 GB	46.6 tok/s	Runs great	57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	47.3 GB	384 GB	36.1 tok/s	Runs great	64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	49.7 GB	384 GB	29.8 tok/s	Runs well	65Good quality (B) · 65 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	52.4 GB	384 GB	25.0 tok/s	Runs well	67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	58.1 GB	384 GB	18.4 tok/s	Runs well	68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	80.7 GB	384 GB	8.5 tok/s	Slow	68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab) 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

67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q6_K · 63.6 tok/s · Runs great
65Good quality (B) · 65 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q5_K_M · 42.6 tok/s · Runs great
65Good quality (B) · 65 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q5_K_M · 39.5 tok/s · Runs great
64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q4_K_M · 42.3 tok/s · Runs great
57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q3_K_M · 44.4 tok/s · Runs well (tight fit)
57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q3_K_M · 48.6 tok/s · Runs well (tight fit)

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.