Check my GPU

on

Can the NVIDIA GB10 (128 GB) run Qwen3.5 122B-A10B?

89 ptsExcellent (S) · 89 of 100 points: Model quality 39.3/45, Memory fit 25.0/25, Speed 9.7/15, Memory use 15.0/15

Yes, it runs well

Runs well. At Q4_K_M it needs about 86.3 GB of 115 GB usable, with an estimated speed of 16.8 tok/s.

Best quant
Q4_K_M
Generation speed
16.8 tok/s
Prompt processing
2,232 tok/s
First token (1K prompt)
0.5 s
Largest safe context
256K

Download Qwen3.5 122B-A10B

Recommended for the NVIDIA GB10 (128 GB): Q4_K_M. 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 qwen3.5:122b-a10b-q4_K_M

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 Q4_K_M files (opens in a new tab)

huggingface.co/unsloth/Qwen3.5-122B-A10B-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Qwen3.5-122B-A10B-GGUF

Original weights · Hugging Face

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

huggingface.co/Qwen/Qwen3.5-122B-A10B (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 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.39.3 / 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.9.7 / 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
Total89.0 / 10089 ptsExcellent (S) · 89 of 100 points: Model quality 39.3/45, Memory fit 25.0/25, Speed 9.7/15, 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 NVIDIA GB10 (128 GB)

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 60.1 GB 115 GB 27.5 tok/s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 29.0/45, Memory fit 25.0/25, Speed 12.4/15, Memory use 12.0/15 GGUF (UD-Q2_K_XL) (opens in a new tab)
Q3_K_M 71.3 GB 115 GB 21.7 tok/s Runs well 85 ptsExcellent (S) · 85 of 100 points: Model quality 34.8/45, Memory fit 25.0/25, Speed 11.0/15, Memory use 14.3/15 GGUF · folder (opens in a new tab)
Q4_K_M 86.3 GB 115 GB 16.8 tok/s Runs well 89 ptsExcellent (S) · 89 of 100 points: Model quality 39.3/45, Memory fit 25.0/25, Speed 9.7/15, Memory use 15.0/15 GGUF · folder (opens in a new tab)
Q5_K_M 98.8 GB 115 GB 13.8 tok/s Tight fit 87 ptsExcellent (S) · 87 of 100 points: Model quality 40.2/45, Memory fit 24.0/25, Speed 8.8/15, Memory use 15.0/15 GGUF · folder (opens in a new tab)
Q6_K 113 GB 115 GB 11.6 tok/s Tight fit 88 ptsExcellent (S) · 88 of 100 points: Model quality 41.0/45, Memory fit 24.0/25, Speed 8.1/15, Memory use 15.0/15 GGUF · folder (opens in a new tab)
Q8_0 143 GB 115 GB — Won't run 12 ptsWon't run (F) · 12 of 100 points: Model quality 12.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 GGUF · folder (opens in a new tab)
F16 260 GB 115 GB — Won't run 12 ptsWon't run (F) · 12 of 100 points: Model quality 12.4/45, 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.