Check my GPU

on

Can the Apple M2 Ultra (192 GB) run Qwen3.5 35B-A3B?

89 ptsExcellent (S) · 89 of 100 points: Model quality 41.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.1/15

Yes, it runs well

Runs well. At Q8_0 it needs about 50.4 GB of 144 GB usable, with an estimated speed of 71.7 tok/s.

Best quant
Q8_0
Generation speed
71.7 tok/s
Prompt processing
5,621 tok/s
First token (1K prompt)
0.3 s
Largest safe context
256K

Download Qwen3.5 35B-A3B

Recommended for the Apple M2 Ultra (192 GB): Q8_0. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

ollama run qwen3.5:35b-a3b-q8_0

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q8_0 file (opens in a new tab)

huggingface.co/unsloth/Qwen3.5-35B-A3B-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Qwen3.5-35B-A3B-GGUF:Q8_0

Original weights · Hugging Face

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

huggingface.co/Qwen/Qwen3.5-35B-A3B (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/QwenLM/Qwen3.8 (opens in a new tab)

git clone https://github.com/QwenLM/Qwen3.8

Qwen’s current repo: Qwen3.5 and Qwen3.6 redirect here.

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

How the S 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.41.9 / 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.15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.8.1 / 15
Total89.9 / 10089 ptsExcellent (S) · 89 of 100 points: Model quality 41.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.1/15

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

Every quantization on the Apple M2 Ultra (192 GB)

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 26.7 GB 144 GB 231 tok/s Runs well 73 ptsGreat (A) · 73 of 100 points: Model quality 29.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.3/15 GGUF (UD-Q2_K_XL) (opens in a new tab)
Q3_K_M 29.9 GB 144 GB 182 tok/s Runs well 79 ptsGreat (A) · 79 of 100 points: Model quality 35.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.8/15 GGUF (opens in a new tab)
Q4_K_M 34.2 GB 144 GB 141 tok/s Runs well 85 ptsExcellent (S) · 85 of 100 points: Model quality 39.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.5/15 GGUF (opens in a new tab)
Q5_K_M 37.8 GB 144 GB 116 tok/s Runs well 86 ptsExcellent (S) · 86 of 100 points: Model quality 40.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.1/15 GGUF (opens in a new tab)
Q6_K 41.8 GB 144 GB 97.8 tok/s Runs well 88 ptsExcellent (S) · 88 of 100 points: Model quality 41.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15 GGUF (opens in a new tab)
Q8_0 50.4 GB 144 GB 71.7 tok/s Runs well 89 ptsExcellent (S) · 89 of 100 points: Model quality 41.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.1/15 GGUF (opens in a new tab)
F16 84.2 GB 144 GB 33.1 tok/s Runs well 93 ptsExcellent (S) · 93 of 100 points: Model quality 41.9/45, Memory fit 25.0/25, Speed 13.6/15, Memory use 13.5/15 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.