Mistral Large 2 (123B) on Apple M3 Ultra (256 GB)

Can the Apple M3 Ultra (256 GB) run Mistral Large 2 (123B)?

79 pts

Yes, it runs well

Runs well. At Q6_K it needs about 120 GB of 192 GB usable, with an estimated speed of 4.9 tok/s.

Best quant: Q6_K
Generation speed: 4.9 tok/s
Prompt processing: 143 tok/s
First token (1K prompt): 7.2 s
Largest safe context: 128K

Download Mistral Large 2 (123B)

Recommended for the Apple M3 Ultra (256 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.

ollama run mistral-large:123b-instruct-2407-q6_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 Q6_K files (opens in a new tab)

huggingface.co/bartowski/Mistral-Large-Instruct-2407-GGUF (opens in a new tab)

ollama run hf.co/bartowski/Mistral-Large-Instruct-2407-GGUF

Original weights · Hugging Face

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

huggingface.co/mistralai/Mistral-Large-Instruct-2407 (opens in a new tab)

Free Hugging Face account needed: accept the license on the model page and the download starts right away.

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 A 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.	34.7 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	5.2 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	14.4 / 15
Total	79.4 / 100	79 ptsGreat (A) · 79 of 100 points: Model quality 34.7/45, Memory fit 25.0/25, Speed 5.2/15, Memory use 14.4/15

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

Every quantization on the Apple M3 Ultra (256 GB)

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	68.1 GB	192 GB	11.6 tok/s	Runs well	65 ptsGood (B) · 65 of 100 points: Model quality 24.6/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.2/15	GGUF (opens in a new tab)
`Q3_K_M`	79.2 GB	192 GB	9.1 tok/s	Runs well	71 ptsGood (B) · 71 of 100 points: Model quality 29.5/45, Memory fit 25.0/25, Speed 7.2/15, Memory use 9.5/15	GGUF · folder (opens in a new tab)
`Q4_K_M`	93.9 GB	192 GB	7.0 tok/s	Runs well	75 ptsGreat (A) · 75 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 6.3/15, Memory use 11.3/15	GGUF · folder (opens in a new tab)
`Q5_K_M`	106 GB	192 GB	5.8 tok/s	Runs well	77 ptsGreat (A) · 77 of 100 points: Model quality 34.0/45, Memory fit 25.0/25, Speed 5.7/15, Memory use 12.8/15	GGUF · folder (opens in a new tab)
`Q6_K`	120 GB	192 GB	4.9 tok/s	Runs well	79 ptsGreat (A) · 79 of 100 points: Model quality 34.7/45, Memory fit 25.0/25, Speed 5.2/15, Memory use 14.4/15	GGUF · folder (opens in a new tab)
`Q8_0`	149 GB	192 GB	3.6 tok/s	Runs well	79 ptsGreat (A) · 79 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 4.5/15, Memory use 15.0/15	GGUF · folder (opens in a new tab)
`F16`	265 GB	192 GB	—	Won't run	10 ptsWon't run (F) · 10 of 100 points: Model quality 10.5/45, 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

82 ptsGreat (A) · 82 of 100 points: Model quality 33.3/45, Memory fit 24.0/25, Speed 10.0/15, Memory use 15.0/15 NVIDIA RTX PRO 6000 Blackwell Q4_K_M · 17.9 tok/s
79 ptsGreat (A) · 79 of 100 points: Model quality 34.7/45, Memory fit 25.0/25, Speed 5.2/15, Memory use 15.0/15 Apple M2 Ultra (192 GB) Q6_K · 4.8 tok/s
77 ptsGreat (A) · 77 of 100 points: Model quality 33.3/45, Memory fit 24.0/25, Speed 5.1/15, Memory use 15.0/15 Apple M4 Max (128 GB) Q4_K_M · 4.7 tok/s
77 ptsGreat (A) · 77 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 3.9/15, Memory use 15.0/15 NVIDIA GB10 (128 GB) Q4_K_M · 2.7 tok/s
75 ptsGreat (A) · 75 of 100 points: Model quality 33.3/45, Memory fit 24.0/25, Speed 3.5/15, Memory use 15.0/15 AMD Ryzen AI Max+ 395 (128 GB) Q4_K_M · 2.2 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.