Check my GPU

on

Can the Apple M1 Max (64 GB) run Phi-3.5 MoE (42B-A6.6B)?

77 ptsGreat (A) · 77 of 100 points: Model quality 23.9/45, Memory fit 25.0/25, Speed 13.4/15, Memory use 14.9/15

Yes, it runs well

Runs well. At Q4_K_M it needs about 31.1 GB of 48.0 GB usable, with an estimated speed of 32.0 tok/s.

Best quant
Q4_K_M
Generation speed
32.0 tok/s
Prompt processing
977 tok/s
First token (1K prompt)
1.0 s
Largest safe context
128K

Download Phi-3.5 MoE (42B-A6.6B)

Recommended for the Apple M1 Max (64 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/lmstudio-community/Phi-3.5-MoE-instruct-GGUF (opens in a new tab)

ollama run hf.co/lmstudio-community/Phi-3.5-MoE-instruct-GGUF:Q4_K_M

Original weights · Hugging Face

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

huggingface.co/microsoft/Phi-3.5-MoE-instruct (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Microsoft. The weights themselves download from Hugging Face.

github.com/microsoft/PhiCookBook (opens in a new tab)

git clone https://github.com/microsoft/PhiCookBook

Microsoft’s official Phi cookbook: setup, inference and fine-tuning guides.

Links checked 7 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.23.9 / 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.13.4 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.14.9 / 15
Total77.3 / 10077 ptsGreat (A) · 77 of 100 points: Model quality 23.9/45, Memory fit 25.0/25, Speed 13.4/15, Memory use 14.9/15

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

Every quantization on the Apple M1 Max (64 GB)

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 22.3 GB 48.0 GB 52.6 tok/s Runs well 68 ptsGood (B) · 68 of 100 points: Model quality 17.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.7/15 GGUF files (opens in a new tab)
Q3_K_M 26.0 GB 48.0 GB 41.4 tok/s Runs well 73 ptsGreat (A) · 73 of 100 points: Model quality 21.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.5/15 GGUF (Q3_K_L) (opens in a new tab)
Q4_K_M 31.1 GB 48.0 GB 32.0 tok/s Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 23.9/45, Memory fit 25.0/25, Speed 13.4/15, Memory use 14.9/15 GGUF (opens in a new tab)
Q5_K_M 35.2 GB 48.0 GB 26.5 tok/s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 24.4/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 15.0/15 GGUF files (opens in a new tab)
Q6_K 39.8 GB 48.0 GB 22.2 tok/s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 24.9/45, Memory fit 25.0/25, Speed 11.2/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q8_0 49.9 GB 48.0 GB 13.9 tok/s Runs with offload 59 ptsGood (B) · 59 of 100 points: Model quality 25.2/45, Memory fit 10.0/25, Speed 8.8/15, Memory use 15.0/15 GGUF (opens in a new tab)
F16 89.3 GB 48.0 GB — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, 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.