Mistral Small 3.1 24B on Apple M6 (16 GB)

Can the Apple M6 (16 GB) run Mistral Small 3.1 24B?

Yes, but slowly (far over GPU memory limit)

Slow (far over GPU memory limit). At Q2_K it needs about 12.4 GB of 10.7 GB usable, with an estimated speed of 9.4 tok/s.

Best quant: Q2_K
Generation speed: 9.4 tok/s
Prompt processing: 147 tok/s
First token (1K prompt): 7.0 s
Largest safe context: —

Best app to run it on the Apple M6 (16 GB)

On macOS

LM Studio

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

Splits the model between GPU memory and system RAM, which this setup needs.
Point-and-click: search, download and chat in one window.

Open Mistral Small 3.1 24B in LM Studio

Ollama Splits the model between GPU memory and system RAM, which this setup needs.
llama.cpp Splits the model between GPU memory and system RAM, which this setup needs.

Want an agent? Mistral Small 3.1 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 3.1 24B

Recommended for the Apple M6 (16 GB): Q2_K. 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-small3.1:24b

Quantized files · GGUF

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

Download the Q2_K (IQ2_M) file (opens in a new tab)

huggingface.co/ggml-org/Mistral-Small-3.1-24B-Instruct-2503-GGUF (opens in a new tab)

ollama run hf.co/ggml-org/Mistral-Small-3.1-24B-Instruct-2503-GGUF:IQ2_M

Original weights · Hugging Face

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

huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503 (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 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q2_K, 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 Slowfar over GPU memory limit: How well it runs on the Apple M6 (16 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.	20.8 / 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.	4.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	7.3 / 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
Match score	47.1 / 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 M6 (16 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	12.4 GB	10.7 GB	9.4 tok/s	Slowfar over GPU memory limit	46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (IQ2_M) (opens in a new tab)
`Q3_K_M`	14.6 GB	10.7 GB	—	Won't run	55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q4_K_M`	17.4 GB	10.7 GB	—	Won't run	62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.
`Q5_K_M`	19.8 GB	10.7 GB	—	Won't run	64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q6_K`	22.5 GB	10.7 GB	—	Won't run	65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q8_0`	28.2 GB	10.7 GB	—	Won't run	66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.
`F16`	50.8 GB	10.7 GB	—	Won't run	66Good quality (B) · 66 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

65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q6_K · 63.6 tok/s · Runs great
64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q5_K_M · 42.6 tok/s · Runs great
64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q5_K_M · 39.5 tok/s · Runs great
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q4_K_M · 42.3 tok/s · Runs great
55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 78/100 (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)
55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q3_K_M · 48.7 tok/s · Runs well (tight fit)

Quick answers

How much memory does Mistral Small 3.1 24B need on the M6 16GB?

At Q2_K it needs about 12.4 GB. The M6 16GB has 10.7 GB usable.

How fast is Mistral Small 3.1 24B on the M6 16GB?

About 9.4 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Mistral Small 3.1 24B should I use on the M6 16GB?

Q2_K. 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.