Benchmark result
empero-ai/Qwen3.8-35B-A3B-Distill-GGUF:Q2_K on Tesla P100-PCIE-16GB — 52.1 tok/s
Measured with unsloth manual on October 31, 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
toolunsloth manual
modelempero-ai/Qwen3.8-35B-A3B-Distill-GGUF:Q2_K (Q2_K)
context65,536
thinkingon
clientv0.4.98+102
Set those in unsloth, then:
llm-benchmark benchmark --model "empero-ai/Qwen3.8-35B-A3B-Distill-GGUF:Q2_K" --tool "unsloth"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.