Mixtral 8x7B Instruct on Apple M2 Pro (32 GB)

Can the Apple M2 Pro (32 GB) run Mixtral 8x7B Instruct?

48 pts

Yes, with part of the model in system RAM

Runs with offload. At Q2_K it needs about 22.1 GB of 21.4 GB usable, with an estimated speed of 11.4 tok/s.

Best quant: Q2_K
Generation speed: 11.4 tok/s
Prompt processing: 327 tok/s
First token (1K prompt): 3.1 s
Largest safe context: 3K

Download Mixtral 8x7B Instruct

Recommended for the Apple M2 Pro (32 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.

ollama run mixtral:8x7b-instruct-v0.1-q2_K

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

Quantized files · GGUF

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

Download the Q2_K file (opens in a new tab)

huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF (opens in a new tab)

ollama run hf.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF:Q2_K

Original weights · Hugging Face

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

huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1 (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)

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

Mistral AI’s official inference code.

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

How the C grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	15.8 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.	10.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	8.0 / 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
Total	48.8 / 100	48 ptsUsable (C) · 48 of 100 points: Model quality 15.8/45, Memory fit 10.0/25, Speed 8.0/15, Memory use 15.0/15

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every quantization on the Apple M2 Pro (32 GB)

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	22.1 GB	21.4 GB	11.4 tok/s	Runs with offload	48 ptsUsable (C) · 48 of 100 points: Model quality 15.8/45, Memory fit 10.0/25, Speed 8.0/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q3_K_M`	26.3 GB	21.4 GB	9.0 tok/s	Heavy offload	45 ptsUsable (C) · 45 of 100 points: Model quality 18.9/45, Memory fit 4.0/25, Speed 7.1/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q4_K_M`	31.9 GB	21.4 GB	—	Won't run	6 ptsWon't run (F) · 6 of 100 points: Model quality 6.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF (opens in a new tab)
`Q5_K_M`	36.5 GB	21.4 GB	—	Won't run	6 ptsWon't run (F) · 6 of 100 points: Model quality 6.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF (opens in a new tab)
`Q6_K`	41.7 GB	21.4 GB	—	Won't run	6 ptsWon't run (F) · 6 of 100 points: Model quality 6.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF (opens in a new tab)
`Q8_0`	52.9 GB	21.4 GB	—	Won't run	6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF (opens in a new tab)
`F16`	96.8 GB	21.4 GB	—	Won't run	6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	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

75 ptsGreat (A) · 75 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.5/15 NVIDIA RTX PRO 6000 Blackwell Q8_0 · 43.4 tok/s
75 ptsGreat (A) · 75 of 100 points: Model quality 21.4/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5090 Q4_K_M · 85.3 tok/s
72 ptsGreat (A) · 72 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 11.2/15, Memory use 15.0/15 Apple M4 Max (64 GB) Q4_K_M · 22.4 tok/s
70 ptsGood (B) · 70 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 9.6/15, Memory use 15.0/15 Apple M1 Max (64 GB) Q4_K_M · 16.4 tok/s
69 ptsGood (B) · 69 of 100 points: Model quality 15.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 7900 XTX Q2_K · 64.6 tok/s
69 ptsGood (B) · 69 of 100 points: Model quality 15.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 3090 Q2_K · 73.1 tok/s

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.