Benchmark result
Whittle-Qwen-3.8-35B-A3B-Q3_K_M on 2× NVIDIA GeForce RTX 5060 — 76.6 tok/s
Measured with llama.cpp b11235-6c7a87f7e on September 28, 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.
Reproduce this run
toolllama.cpp b11235-6c7a87f7e
modelWhittle-Qwen-3.8-35B-A3B-Q3_K_M (Q3_K_M)
context262,144
thinkingon
samplingtemperature 0.699999988079071 · top_p 0.800000011920929 · top_k 20 · min_p 0 · presence_penalty 0 · repeat_penalty 1.0499999523162842
clientv0.4.82+98
Set those in llama.cpp, then:
llm-benchmark benchmark --model "Whittle-Qwen-3.8-35B-A3B-Q3_K_M" --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.