Benchmark result
mistral-small:Q5 on AMD Radeon Graphics — 39.3 tok/s
Measured with llama.cpp b11749-1d88cb05f on October 21, 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
mistral-small:Q5 on other hardware
- 39.3tok/s65.8Unknown hardwarethis run
- 39.3tok/s72.0Unknown hardware
Reproduce this run
toolllama.cpp b11749-1d88cb05f
modelmistral-small:Q5
context65,536
thinkingon
samplingtemperature 0.15000000596046448 · top_p 1 · top_k 40 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1
clientv0.4.96+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "mistral-small:Q5" --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.