Benchmark result
Qwen3.6-35B-A3B-UD-IQ2_XXS on AMD Radeon RX 7900 XTX — 204.0 tok/s
Measured with lm-studio manual on October 2, 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
9th fastest of 12 runs of this model on AMD Radeon RX 7900 XTX · median 210.3 tok/s.
sort
Compare the nearest 5 →
Reproduce this run
toollm-studio manual
modelQwen3.6-35B-A3B-UD-IQ2_XXS
context65,536
thinkingon
clientv0.4.85+101
Set those in lm-studio, then:
llm-benchmark benchmark --model "Qwen3.6-35B-A3B-UD-IQ2_XXS" --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.