Check my GPU

on

Can the AMD Radeon RX 9070 XT run Qwen3.5 9B?

87 ptsExcellent (S) · 87 of 100 points: Model quality 33.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.8/15

Yes, it runs well

Runs well. At Q6_K it needs about 9.6 GB of 16.0 GB usable, with an estimated speed of 48.6 tok/s.

Best quant
Q6_K
Generation speed
48.6 tok/s
Prompt processing
6,251 tok/s
First token (1K prompt)
0.3 s
Largest safe context
199K

Download Qwen3.5 9B

Recommended for the AMD Radeon RX 9070 XT: Q6_K. 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 qwen3.5:9b

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 Q6_K file (opens in a new tab)

huggingface.co/unsloth/Qwen3.5-9B-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Qwen3.5-9B-GGUF:Q6_K

Original weights · Hugging Face

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

huggingface.co/Qwen/Qwen3.5-9B (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.33.9 / 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.13.8 / 15
Total87.7 / 10087 ptsExcellent (S) · 87 of 100 points: Model quality 33.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.8/15

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

Every quantization on the AMD Radeon RX 9070 XT

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 5.5 GB 16.0 GB 115 tok/s Runs well 71 ptsGood (B) · 71 of 100 points: Model quality 23.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.0/15 GGUF (UD-Q2_K_XL) (opens in a new tab)
Q3_K_M 6.4 GB 16.0 GB 90.6 tok/s Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 28.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.2/15 GGUF (opens in a new tab)
Q4_K_M 7.6 GB 16.0 GB 70.1 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 32.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15 GGUF (opens in a new tab)
Q5_K_M 8.5 GB 16.0 GB 57.9 tok/s Runs well 85 ptsExcellent (S) · 85 of 100 points: Model quality 33.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.3/15 GGUF (opens in a new tab)
Q6_K 9.6 GB 16.0 GB 48.6 tok/s Runs well 87 ptsExcellent (S) · 87 of 100 points: Model quality 33.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.8/15 GGUF (opens in a new tab)
Q8_0 11.9 GB 16.0 GB 35.7 tok/s Runs well 88 ptsExcellent (S) · 88 of 100 points: Model quality 34.2/45, Memory fit 25.0/25, Speed 14.2/15, Memory use 15.0/15 GGUF (opens in a new tab)
F16 21.0 GB 16.0 GB 5.7 tok/s Runs with offload 64 ptsGood (B) · 64 of 100 points: Model quality 34.2/45, Memory fit 10.0/25, Speed 5.7/15, Memory use 15.0/15 GGUF (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.