Check my GPU

on

Can the Apple M2 Pro (32 GB) run Phi-3 Small 8K Instruct?

64 ptsGood (B) · 64 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 12.7/15, Memory use 8.5/15

Yes, it runs well

Runs well. At Q4_K_M it needs about 7.9 GB of 21.4 GB usable, with an estimated speed of 28.6 tok/s.

Best quant
Q4_K_M
Generation speed
28.6 tok/s
Prompt processing
571 tok/s
First token (1K prompt)
1.8 s
Largest safe context
8K

Download Phi-3 Small 8K Instruct

Original weights · Hugging Face

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

huggingface.co/microsoft/Phi-3-small-8k-instruct (opens in a new tab)

No sign-in needed.

Links checked 6 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.18.8 / 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.12.7 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.8.5 / 15
Total65.0 / 10064 ptsGood (B) · 64 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 12.7/15, Memory use 8.5/15

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 6.3 GB 21.4 GB 47.0 tok/s Runs well 60 ptsGood (B) · 60 of 100 points: Model quality 13.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.8/15 All files (opens in a new tab)
Q3_K_M 7.0 GB 21.4 GB 37.0 tok/s Runs well 63 ptsGood (B) · 63 of 100 points: Model quality 16.6/45, Memory fit 25.0/25, Speed 14.4/15, Memory use 7.5/15 All files (opens in a new tab)
Q4_K_M 7.9 GB 21.4 GB 28.6 tok/s Runs well 64 ptsGood (B) · 64 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 12.7/15, Memory use 8.5/15 All files (opens in a new tab)
Q5_K_M 8.6 GB 21.4 GB 23.6 tok/s Runs well 65 ptsGood (B) · 65 of 100 points: Model quality 19.2/45, Memory fit 25.0/25, Speed 11.5/15, Memory use 9.3/15 All files (opens in a new tab)
Q6_K 9.4 GB 21.4 GB 19.8 tok/s Runs well 65 ptsGood (B) · 65 of 100 points: Model quality 19.6/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 10.2/15 All files (opens in a new tab)
Q8_0 11.2 GB 21.4 GB 14.6 tok/s Runs well 65 ptsGood (B) · 65 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 9.1/15, Memory use 12.1/15 All files (opens in a new tab)
F16 18.2 GB 21.4 GB 6.7 tok/s Runs well 65 ptsGood (B) · 65 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 6.1/15, 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.