Check my GPU

on

Can the Apple M2 Pro (32 GB) run OLMo 7B Instruct?

52 ptsUsable (C) · 52 of 100 points: Model quality 5.3/45, Memory fit 25.0/25, Speed 14.9/15, Memory use 7.3/15

Yes, it runs well

Runs well. At Q3_K_M it needs about 6.8 GB of 21.4 GB usable, with an estimated speed of 39.7 tok/s.

Best quant
Q3_K_M
Generation speed
39.7 tok/s
Prompt processing
612 tok/s
First token (1K prompt)
1.7 s
Largest safe context
2K

Download OLMo 7B Instruct

Original weights · Hugging Face

Full-precision files from Ai2, for fine-tuning, vLLM, Transformers.

huggingface.co/allenai/OLMo-7B-Instruct-hf (opens in a new tab)

No sign-in needed.

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

How the C 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.5.3 / 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.14.9 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.7.3 / 15
Total52.5 / 10052 ptsUsable (C) · 52 of 100 points: Model quality 5.3/45, Memory fit 25.0/25, Speed 14.9/15, Memory use 7.3/15

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 6.1 GB 21.4 GB 50.4 tok/s Runs well 51 ptsUsable (C) · 51 of 100 points: Model quality 4.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15 All files (opens in a new tab)
Q3_K_M 6.8 GB 21.4 GB 39.7 tok/s Runs well 52 ptsUsable (C) · 52 of 100 points: Model quality 5.3/45, Memory fit 25.0/25, Speed 14.9/15, Memory use 7.3/15 All files (opens in a new tab)
Q4_K_M 7.6 GB 21.4 GB 30.7 tok/s Runs well 52 ptsUsable (C) · 52 of 100 points: Model quality 6.0/45, Memory fit 25.0/25, Speed 13.1/15, Memory use 8.2/15 All files (opens in a new tab)
Q5_K_M 8.3 GB 21.4 GB 25.3 tok/s Runs well 51 ptsUsable (C) · 51 of 100 points: Model quality 6.1/45, Memory fit 25.0/25, Speed 11.9/15, Memory use 8.9/15 All files (opens in a new tab)
Q6_K 9.0 GB 21.4 GB 21.3 tok/s Runs well 51 ptsUsable (C) · 51 of 100 points: Model quality 6.2/45, Memory fit 25.0/25, Speed 10.9/15, Memory use 9.7/15 All files (opens in a new tab)
Q8_0 10.7 GB 21.4 GB 15.6 tok/s Runs well 52 ptsUsable (C) · 52 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 9.4/15, Memory use 11.5/15 All files (opens in a new tab)
F16 17.2 GB 21.4 GB 7.2 tok/s Runs well 52 ptsUsable (C) · 52 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 6.4/15, Memory use 15.0/15 Original weights (opens in a new tab)

Memory figures assume 2K 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.