Benchmark result
qwen/qwen3.6-35b-a3b on AMD Radeon RX 7900 XTX — 32.4 tok/s
Measured with LM Studio on April 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
5th fastest of 6 runs of this model on AMD Radeon RX 7900 XTX · median 32.6 tok/s.
sort
- 146.1tok/s74.3LM Studio
- 232.9tok/s62.3LM Studio
- 332.7tok/s50.4LM Studio
- 432.5tok/s68.5LM Studio
- 532.4tok/s70.7LM Studiothis run
- 69.9tok/s82.6LM Studio
Reproduce this run
toolLM Studio
modelqwen/qwen3.6-35b-a3b
context16,384
clientv0.4.20+97
Set those in LM Studio, then:
llm-benchmark benchmark --model "qwen/qwen3.6-35b-a3b" --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.