Benchmark result
unsloth-qwen3.8:TOOLING on AMD Radeon Graphics — 31.0 tok/s
Measured with llama.cpp b11718-547208dca on October 18, 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
unsloth-qwen3.8:TOOLING on other hardware
- 31.1tok/s90.6Unknown hardware
- 31.0tok/s67.5Unknown hardwarethis run
- 31.0tok/s70.4Unknown hardware
Reproduce this run
toolllama.cpp b11718-547208dca
modelunsloth-qwen3.8:TOOLING
context8,192
effortxhigh (model default)
samplingtemperature 0.699999988079071 · top_p 0.800000011920929 · top_k 20 · min_p 0.05000000074505806 · presence_penalty 1.5 · repeat_penalty 1
clientv0.4.96+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "unsloth-qwen3.8:TOOLING" --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.