on

Can the Apple M2 Ultra (192 GB) run Mixtral 8x7B Instruct?

49Fair quality (C) · 49 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.

Yes, it runs great

Runs great. At Q6_K it needs about 51.5 GB of 144 GB usable, with an estimated speed of 39.1 tok/s.

Best quant
Q6_K
Generation speed
39.1 tok/s
Prompt processing
1,307 tok/s
First token (1K prompt)
0.8 s
Largest safe context
32K

Best app to run it on the Apple M2 Ultra (192 GB)

On macOS

LM Studio

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

  • Runs the MLX build, typically 10–20% faster than GGUF for a model with 12.9B active parameters on Apple silicon.
  • Point-and-click: search, download and chat in one window.

Open Mixtral 8x7B Instruct in LM Studio

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

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 Mixtral 8x7B Instruct

Recommended for the Apple M2 Ultra (192 GB): Q6_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 mixtral:8x7b-instruct-v0.1-q6_K

Quantized files · GGUF

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

Download the Q6_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:Q6_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)

Mistral AI’s official inference code.

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

Links checked 1 day ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 49Fair quality (C) · 49 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.
How capable the model itself is at Q6_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 Runs great
How well it runs on the Apple M2 Ultra (192 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.22.3 / 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.14.8 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.8.3 / 15
Match score70.4 / 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 M2 Ultra (192 GB)

Quant Memory needed Available Speed Runs Quality Download
Q2_K 31.9 GB 144 GB 80.6 tok/s Runs great 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q3_K_M 36.1 GB 144 GB 66.5 tok/s Runs great 42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q4_K_M 41.7 GB 144 GB 53.7 tok/s Runs great 47Fair quality (C) · 47 of 100: how capable the model is at Q4_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)
Q5_K_M 46.4 GB 144 GB 45.5 tok/s Runs great 48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q6_K 51.5 GB 144 GB 39.1 tok/s Runs great 49Fair quality (C) · 49 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 62.7 GB 144 GB 29.6 tok/s Runs well 50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
F16 107 GB 144 GB 14.4 tok/s Runs well 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (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

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?