Check my GPU

on

Can the Apple M2 Pro (32 GB) run MiniCPM3 4B?

62 ptsGood (B) · 62 of 100 points: Model quality 16.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.9/15

Yes, it runs well

Runs well. At Q5_K_M it needs about 5.5 GB of 21.4 GB usable, with an estimated speed of 42.9 tok/s.

Best quant
Q5_K_M
Generation speed
42.9 tok/s
Prompt processing
1,036 tok/s
First token (1K prompt)
1.0 s
Largest safe context
32K

Download MiniCPM3 4B

Quantized files · GGUF

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

huggingface.co/openbmb/MiniCPM3-4B-GGUF (opens in a new tab)

ollama run hf.co/openbmb/MiniCPM3-4B-GGUF

Original weights · Hugging Face

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

huggingface.co/openbmb/MiniCPM3-4B (opens in a new tab)

No sign-in needed.

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

How the B 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.16.6 / 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.5.9 / 15
Total62.5 / 10062 ptsGood (B) · 62 of 100 points: Model quality 16.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.9/15

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 4.2 GB 21.4 GB 85.3 tok/s Runs well 56 ptsUsable (C) · 56 of 100 points: Model quality 12.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.6/15 GGUF files (opens in a new tab)
Q3_K_M 4.6 GB 21.4 GB 67.2 tok/s Runs well 59 ptsGood (B) · 59 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.0/15 GGUF files (opens in a new tab)
Q4_K_M 5.1 GB 21.4 GB 51.9 tok/s Runs well 61 ptsGood (B) · 61 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.5/15 GGUF (opens in a new tab)
Q5_K_M 5.5 GB 21.4 GB 42.9 tok/s Runs well 62 ptsGood (B) · 62 of 100 points: Model quality 16.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.9/15 GGUF files (opens in a new tab)
Q6_K 5.9 GB 21.4 GB 36.0 tok/s Runs well 62 ptsGood (B) · 62 of 100 points: Model quality 16.9/45, Memory fit 25.0/25, Speed 14.2/15, Memory use 6.4/15 GGUF files (opens in a new tab)
Q8_0 6.9 GB 21.4 GB 26.4 tok/s Runs well 61 ptsGood (B) · 61 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 7.5/15 GGUF files (opens in a new tab)
F16 10.7 GB 21.4 GB 12.2 tok/s Runs well 61 ptsGood (B) · 61 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 8.3/15, Memory use 11.6/15 GGUF (opens in a new tab) 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.