Check my GPU

on

Can the Apple M3 Ultra (256 GB) run QVQ 72B Preview?

69 ptsGood (B) · 69 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 7.6/15

Yes, it runs well

Runs well. At Q4_K_M it needs about 63.4 GB of 192 GB usable, with an estimated speed of 11.8 tok/s.

Best quant
Q4_K_M
Generation speed
11.8 tok/s
Prompt processing
240 tok/s
First token (1K prompt)
4.3 s
Largest safe context
32K

Download QVQ 72B Preview

Recommended for the Apple M3 Ultra (256 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/bartowski/QVQ-72B-Preview-GGUF (opens in a new tab)

ollama run hf.co/bartowski/QVQ-72B-Preview-GGUF:Q4_K_M

Original weights · Hugging Face

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

huggingface.co/Qwen/QVQ-72B-Preview (opens in a new tab)

No sign-in needed.

Links checked 5 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.29.1 / 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.8.1 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.7.6 / 15
Total69.8 / 10069 ptsGood (B) · 69 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 7.6/15

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

Every quantization on the Apple M3 Ultra (256 GB)

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 48.0 GB 192 GB 19.4 tok/s Runs well 62 ptsGood (B) · 62 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 10.4/15, Memory use 5.8/15 GGUF (opens in a new tab)
Q3_K_M 54.6 GB 192 GB 15.2 tok/s Runs well 66 ptsGood (B) · 66 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 9.3/15, Memory use 6.6/15 GGUF (opens in a new tab)
Q4_K_M 63.4 GB 192 GB 11.8 tok/s Runs well 69 ptsGood (B) · 69 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 7.6/15 GGUF (opens in a new tab)
Q5_K_M 70.8 GB 192 GB 9.7 tok/s Runs well 70 ptsGood (B) · 70 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 7.4/15, Memory use 8.5/15 GGUF · folder (opens in a new tab)
Q6_K 78.8 GB 192 GB 8.2 tok/s Runs well 71 ptsGood (B) · 71 of 100 points: Model quality 30.3/45, Memory fit 25.0/25, Speed 6.8/15, Memory use 9.5/15 GGUF · folder (opens in a new tab)
Q8_0 96.5 GB 192 GB 6.0 tok/s Runs well 73 ptsGreat (A) · 73 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 5.8/15, Memory use 11.6/15 GGUF · folder (opens in a new tab)
F16 165 GB 192 GB 2.8 tok/s Tight fit 73 ptsGreat (A) · 73 of 100 points: Model quality 30.6/45, Memory fit 24.0/25, Speed 3.9/15, 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.