Benchmark result
qwen-3.8-27b on NVIDIA GeForce RTX 5080 — 55.2 tok/s
Measured with llama.cpp manual on October 13, 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
modelqwen-3.8-27b
context65,536
thinkingon
effortxhigh
think limit8,192 tokens
samplingtemperature 1 · top_p 0.949999988079071 · top_k 20 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1
clientv0.4.92+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "qwen-3.8-27b" --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.