Benchmark result
qwen3.5:9b on AMD Radeon RX 7900 XTX — 19.8 tok/s
Measured with Ollama 0.21.1 on May 3, 2026.
What the model built
Open full screen →The coding scenario asks for a playable game in a single HTML file. This is exactly what the model returned, unedited.
How this run compares
2nd fastest of 5 runs of this model on AMD Radeon RX 7900 XTX · median 18.4 tok/s.
sort
- 1101.4tok/s70.0LM Studio
- 219.8tok/s66.7Ollama · Q4_K_Mthis run
- 318.4tok/s68.5Ollama · Q4_K_M
- 416.6tok/s67.9Ollama · Q4_K_M
- 513.6tok/s60.2Ollama · Q4_K_M
Reproduce this run
toolOllama 0.21.1
modelqwen3.5:9b (Q4_K_M)
context65,536
clientv0.4.20+97
Set those in Ollama, then:
llm-benchmark benchmark --model "qwen3.5:9b" --tool "Ollama"The client prompts for context length and thinking mode, and for the KV cache dtype on Unsloth Studio. Sampling is left at the model default — the values above are what the tool reported using, not overrides the client sent.