Check my GPU

on

Can the Apple M3 Ultra (512 GB) run GLM-4.5 (355B-A32B)?

83 ptsGreat (A) · 83 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 8.7/15, Memory use 15.0/15

Yes, it runs well

Runs well. At Q4_K_M it needs about 253 GB of 384 GB usable, with an estimated speed of 13.5 tok/s.

Best quant
Q4_K_M
Generation speed
13.5 tok/s
Prompt processing
550 tok/s
First token (1K prompt)
1.9 s
Largest safe context
128K

Download GLM-4.5 (355B-A32B)

Recommended for the Apple M3 Ultra (512 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 files (opens in a new tab)

huggingface.co/unsloth/GLM-4.5-GGUF (opens in a new tab)

ollama run hf.co/unsloth/GLM-4.5-GGUF

Original weights · Hugging Face

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

huggingface.co/zai-org/GLM-4.5 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/zai-org/GLM-4.5 (opens in a new tab)

git clone https://github.com/zai-org/GLM-4.5

Links checked 10 hours 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.35.1 / 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.8.7 / 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
Total83.8 / 10083 ptsGreat (A) · 83 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 8.7/15, 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 (512 GB)

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 178 GB 384 GB 22.2 tok/s Runs well 72 ptsGreat (A) · 72 of 100 points: Model quality 25.8/45, Memory fit 25.0/25, Speed 11.2/15, Memory use 10.7/15 GGUF · folder (opens in a new tab)
Q3_K_M 210 GB 384 GB 17.5 tok/s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 31.0/45, Memory fit 25.0/25, Speed 9.9/15, Memory use 12.6/15 GGUF · folder (opens in a new tab)
Q4_K_M 253 GB 384 GB 13.5 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 8.7/15, Memory use 15.0/15 GGUF · folder (opens in a new tab)
Q5_K_M 289 GB 384 GB 11.2 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 35.8/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 15.0/15 GGUF · folder (opens in a new tab)
Q6_K 328 GB 384 GB 9.4 tok/s Tight fit 82 ptsGreat (A) · 82 of 100 points: Model quality 36.5/45, Memory fit 24.0/25, Speed 7.3/15, Memory use 15.0/15 GGUF · folder (opens in a new tab)
Q8_0 414 GB 384 GB 5.9 tok/s Runs with offload 67 ptsGood (B) · 67 of 100 points: Model quality 36.9/45, Memory fit 10.0/25, Speed 5.7/15, Memory use 15.0/15 GGUF · folder (opens in a new tab)
F16 751 GB 384 GB — Won't run 11 ptsWon't run (F) · 11 of 100 points: Model quality 11.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 GGUF · folder (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.