Check my GPU

on

Can the Apple M3 Ultra (512 GB) run Leanstral 119B-A6B?

80 ptsGreat (A) · 80 of 100 points: Model quality 33.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.8/15

Yes, it runs well

Runs well. At Q6_K it needs about 129 GB of 384 GB usable, with an estimated speed of 46.2 tok/s.

Best quant
Q6_K
Generation speed
46.2 tok/s
Prompt processing
2,709 tok/s
First token (1K prompt)
0.4 s
Largest safe context
256K

Download Leanstral 119B-A6B

Original weights · Hugging Face

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

huggingface.co/mistralai/Leanstral-2603 (opens in a new tab)

No sign-in needed.

Links checked 6 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.33.0 / 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.15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.7.8 / 15
Total80.7 / 10080 ptsGreat (A) · 80 of 100 points: Model quality 33.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.8/15

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

Every quantization on the Apple M3 Ultra (512 GB)

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 79.3 GB 384 GB 109 tok/s Runs well 68 ptsGood (B) · 68 of 100 points: Model quality 23.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.8/15 All files (opens in a new tab)
Q3_K_M 90.0 GB 384 GB 86.1 tok/s Runs well 73 ptsGreat (A) · 73 of 100 points: Model quality 28.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.4/15 All files (opens in a new tab)
Q4_K_M 104 GB 384 GB 66.6 tok/s Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 31.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15 All files (opens in a new tab)
Q5_K_M 116 GB 384 GB 55.0 tok/s Runs well 79 ptsGreat (A) · 79 of 100 points: Model quality 32.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.0/15 All files (opens in a new tab)
Q6_K 129 GB 384 GB 46.2 tok/s Runs well 80 ptsGreat (A) · 80 of 100 points: Model quality 33.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.8/15 All files (opens in a new tab)
Q8_0 158 GB 384 GB 33.9 tok/s Runs well 81 ptsGreat (A) · 81 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 13.8/15, Memory use 9.5/15 All files (opens in a new tab)
F16 270 GB 384 GB 15.6 tok/s Runs well 82 ptsGreat (A) · 82 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 9.4/15, Memory use 15.0/15 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

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.