Benchmark result
QwenPaw-Flash-4B-Q4_K_M on NVIDIA RTX A6000 — 123.2 tok/s
Measured with llama.cpp manual on October 20, 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 manual
modelQwenPaw-Flash-4B-Q4_K_M (Q4_K_M)
context65,536
thinkingon
think limitnone
clientv0.4.96+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "QwenPaw-Flash-4B-Q4_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.