Check my GPU

on

Can the Apple M3 Ultra (256 GB) run Baichuan M3 235B-A22B?

86 ptsExcellent (S) · 86 of 100 points: Model quality 35.9/45, Memory fit 25.0/25, Speed 10.5/15, Memory use 15.0/15

Yes, it runs well

Runs well. At Q4_K_M it needs about 161 GB of 192 GB usable, with an estimated speed of 19.7 tok/s.

Best quant
Q4_K_M
Generation speed
19.7 tok/s
Prompt processing
800 tok/s
First token (1K prompt)
1.3 s
Largest safe context
40K

Download Baichuan M3 235B-A22B

Recommended for the Apple M3 Ultra (256 GB): Q4_K_M. Every other quantization has its own download link in the table below.

Quantized files · GGUF

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

Download the Q4_K_M file (opens in a new tab)

huggingface.co/mradermacher/Baichuan-M3-235B-i1-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/Baichuan-M3-235B-i1-GGUF:Q4_K_M

Original weights · Hugging Face

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

huggingface.co/baichuan-inc/Baichuan-M3-235B (opens in a new tab)

No sign-in needed.

Links checked 6 days ago against Hugging Face, Ollama and GitHub.

How the S 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.35.9 / 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.10.5 / 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
Total86.4 / 10086 ptsExcellent (S) · 86 of 100 points: Model quality 35.9/45, Memory fit 25.0/25, Speed 10.5/15, 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 M3 Ultra (256 GB)

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 112 GB 192 GB 32.3 tok/s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 13.5/15, Memory use 13.4/15 GGUF (opens in a new tab)
Q3_K_M 133 GB 192 GB 25.4 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 31.8/45, Memory fit 25.0/25, Speed 12.0/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q4_K_M 161 GB 192 GB 19.7 tok/s Runs well 86 ptsExcellent (S) · 86 of 100 points: Model quality 35.9/45, Memory fit 25.0/25, Speed 10.5/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q5_K_M 184 GB 192 GB 16.3 tok/s Tight fit 85 ptsExcellent (S) · 85 of 100 points: Model quality 36.7/45, Memory fit 24.0/25, Speed 9.6/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q6_K 210 GB 192 GB 11.6 tok/s Runs with offload 70 ptsGood (B) · 70 of 100 points: Model quality 37.4/45, Memory fit 10.0/25, Speed 8.1/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q8_0 267 GB 192 GB — Won't run 11 ptsWon't run (F) · 11 of 100 points: Model quality 11.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 GGUF files (opens in a new tab)
F16 488 GB 192 GB — Won't run 11 ptsWon't run (F) · 11 of 100 points: Model quality 11.3/45, 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

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.