Benchmark result
nail-qwen3.6-35b-a3b on AMD Radeon RX 9050 / 9060 XT — 50.7 tok/s
Measured with LM Studio on September 22, 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
3rd fastest of 4 runs of this model on AMD Radeon RX 9050 / 9060 XT · median 50.9 tok/s.
sort
- 152.1tok/s77.3LM Studio
- 251.1tok/s74.5LM Studio
- 350.7tok/s79.0LM Studiothis run
- 450.1tok/s78.6LM Studio
nail-qwen3.6-35b-a3b on other hardware
Reproduce this run
toolLM Studio
modelnail-qwen3.6-35b-a3b
context65,536
thinkingon
clientv0.4.71+98
Set those in LM Studio, then:
llm-benchmark benchmark --model "nail-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.