Benchmark result
Qwen3.6-35B-A3B-GSQ-hybrid on 2× NVIDIA GeForce RTX 5060 — 84.3 tok/s
Measured with llama.cpp b11381-836d57176 on October 3, 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
1st fastest of 2 runs of this model on 2× NVIDIA GeForce RTX 5060 · Multi-GPU · median 83.8 tok/s.
sort
- 184.3tok/s80.2llama.cppthis run
- 283.3tok/s75.6llama.cpp
Reproduce this run
toolllama.cpp b11381-836d57176
modelQwen3.6-35B-A3B-GSQ-hybrid
context262,144
thinkingon
think limitnone
samplingtemperature 0.3330000042915344 · top_p 0.949999988079071 · top_k 20 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1.0499999523162842
clientv0.4.87+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "Qwen3.6-35B-A3B-GSQ-hybrid" --tool "llama.cpp"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.