Check my GPU

on

Can the AMD Ryzen AI 9 HX 370 (DDR5 SO-DIMM) (128 GB) run Qwen3-Next 80B-A3B Thinking?

85 ptsExcellent (S) · 85 of 100 points: Model quality 36.8/45, Memory fit 25.0/25, Speed 9.4/15, Memory use 14.0/15

Yes, it runs well

Runs well. At Q4_K_M it needs about 58.1 GB of 96.0 GB usable, with an estimated speed of 15.8 tok/s.

Best quant
Q4_K_M
Generation speed
15.8 tok/s
Prompt processing
4,919 tok/s
First token (1K prompt)
0.3 s
Largest safe context
256K

Download Qwen3-Next 80B-A3B Thinking

Recommended for the AMD Ryzen AI 9 HX 370 (DDR5 SO-DIMM) (128 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/Qwen/Qwen3-Next-80B-A3B-Thinking-GGUF (opens in a new tab)

ollama run hf.co/Qwen/Qwen3-Next-80B-A3B-Thinking-GGUF:Q4_K_M

Original weights · Hugging Face

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

huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking (opens in a new tab)

No sign-in needed.

Links checked 7 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.36.8 / 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.9.4 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.14.0 / 15
Total85.2 / 10085 ptsExcellent (S) · 85 of 100 points: Model quality 36.8/45, Memory fit 25.0/25, Speed 9.4/15, Memory use 14.0/15

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

Every quantization on the AMD Ryzen AI 9 HX 370 (DDR5 SO-DIMM) (128 GB)

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 41.0 GB 96.0 GB 25.9 tok/s Runs well 74 ptsGreat (A) · 74 of 100 points: Model quality 27.1/45, Memory fit 25.0/25, Speed 12.1/15, Memory use 9.9/15 GGUF files (opens in a new tab)
Q3_K_M 48.3 GB 96.0 GB 20.4 tok/s Runs well 79 ptsGreat (A) · 79 of 100 points: Model quality 32.5/45, Memory fit 25.0/25, Speed 10.7/15, Memory use 11.6/15 GGUF files (opens in a new tab)
Q4_K_M 58.1 GB 96.0 GB 15.8 tok/s Runs well 85 ptsExcellent (S) · 85 of 100 points: Model quality 36.8/45, Memory fit 25.0/25, Speed 9.4/15, Memory use 14.0/15 GGUF (opens in a new tab)
Q5_K_M 66.2 GB 96.0 GB 13.0 tok/s Runs well 86 ptsExcellent (S) · 86 of 100 points: Model quality 37.5/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q6_K 75.2 GB 96.0 GB 11.0 tok/s Runs well 86 ptsExcellent (S) · 86 of 100 points: Model quality 38.3/45, Memory fit 25.0/25, Speed 7.8/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q8_0 94.7 GB 96.0 GB 8.0 tok/s Tight fit 84 ptsGreat (A) · 84 of 100 points: Model quality 38.7/45, Memory fit 24.0/25, Speed 6.7/15, Memory use 15.0/15 GGUF (opens in a new tab)
F16 171 GB 96.0 GB — Won't run 11 ptsWon't run (F) · 11 of 100 points: Model quality 11.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 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.