Benchmark result
qwen3.5-9b on AMD Radeon RX 7900 XTX — 101.4 tok/s
Measured with LM Studio on August 20, 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
1st fastest of 5 runs of this model on AMD Radeon RX 7900 XTX · median 18.4 tok/s.
sort
- 1101.4tok/s70.0LM Studiothis run
- 219.8tok/s66.7Ollama · Q4_K_M
- 318.4tok/s68.5Ollama · Q4_K_M
- 416.6tok/s67.9Ollama · Q4_K_M
- 513.6tok/s60.2Ollama · Q4_K_M
Reproduce this run
toolLM Studio
modelqwen3.5-9b
context8,192
clientv0.4.36+97
Set those in LM Studio, then:
llm-benchmark benchmark --model "qwen3.5-9b" --tool "LM Studio"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.