Benchmark result
qwen3.6-35b-a3b-mtp on AMD Radeon RX 9070/9070 XT/9070 GRE — 27.4 tok/s
Measured with LM Studio on September 15, 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
qwen3.6-35b-a3b-mtp on other hardware
Reproduce this run
toolLM Studio
modelqwen3.6-35b-a3b-mtp
context262,144
clientv0.4.59+97
Set those in LM Studio, then:
llm-benchmark benchmark --model "qwen3.6-35b-a3b-mtp" --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.