Check my GPU

on

Can the Apple M5 Pro (48 GB) run Qwen AgentWorld 35B-A3B?

92 ptsExcellent (S) · 92 of 100 points: Model quality 38.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15

Yes, it runs well

Runs well. At Q5_K_M it needs about 28.3 GB of 36.0 GB usable, with an estimated speed of 44.7 tok/s.

Best quant
Q5_K_M
Generation speed
44.7 tok/s
Prompt processing
1,943 tok/s
First token (1K prompt)
0.5 s
Largest safe context
256K

Download Qwen AgentWorld 35B-A3B

Recommended for the Apple M5 Pro (48 GB): Q5_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 Q5_K_M file (opens in a new tab)

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

ollama run hf.co/unsloth/Qwen-AgentWorld-35B-A3B-GGUF:Q5_K_M

Original weights · Hugging Face

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

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

No sign-in needed.

Links checked 5 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.38.0 / 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.15.0 / 15
Total93.0 / 10092 ptsExcellent (S) · 92 of 100 points: Model quality 38.0/45, Memory fit 25.0/25, Speed 15.0/15, 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 M5 Pro (48 GB)

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 17.5 GB 36.0 GB 88.8 tok/s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 27.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.2/15 GGUF (UD-Q2_K_XL) (opens in a new tab)
Q3_K_M 20.6 GB 36.0 GB 69.9 tok/s Runs well 86 ptsExcellent (S) · 86 of 100 points: Model quality 32.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.2/15 GGUF (opens in a new tab)
Q4_K_M 24.8 GB 36.0 GB 54.1 tok/s Runs well 92 ptsExcellent (S) · 92 of 100 points: Model quality 37.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q5_K_M 28.3 GB 36.0 GB 44.7 tok/s Runs well 92 ptsExcellent (S) · 92 of 100 points: Model quality 38.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q6_K 32.1 GB 36.0 GB 37.5 tok/s Tight fit 92 ptsExcellent (S) · 92 of 100 points: Model quality 38.8/45, Memory fit 24.0/25, Speed 14.5/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q8_0 40.4 GB 36.0 GB 23.4 tok/s Heavy offload 69 ptsGood (B) · 69 of 100 points: Model quality 39.2/45, Memory fit 4.0/25, Speed 11.5/15, Memory use 15.0/15 GGUF (opens in a new tab)
F16 73.0 GB 36.0 GB — Won't run 11 ptsWon't run (F) · 11 of 100 points: Model quality 11.7/45, 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.