Benchmark result
qwen/qwen3.5-35b-a3b on AMD Radeon RX 7900 XTX — 29.2 tok/s
Measured with LM Studio on April 17, 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; the frame only adds a line that tells this page how tall it is.
How this run compares
2nd fastest of 2 runs of this model on AMD Radeon RX 7900 XTX · median 30.6 tok/s.
sort
- 132.0tok/s71.8LM Studio
- 229.2tok/s71.7LM Studiothis run
Reproduce this run
toolLM Studio
modelqwen/qwen3.5-35b-a3b
context16,384
clientv0.4.15+90
Set those in LM Studio, then:
llm-benchmark benchmark --model "qwen/qwen3.5-35b-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.