Benchmark result
Qwen3.8-27B-Turbo-Brilliance-50X-RI-GSQ-RCO-IQ3_XXS-mtp on AMD Radeon RX 7800 XT — 31.5 tok/s
Measured with llama.cpp k8 v4 -1 budget manual on October 12, 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
3rd fastest of 3 runs of this model on AMD Radeon RX 7800 XT · median 34.6 tok/s.
sort
- 146.4tok/s82.9llama.cpp k8 v4 -1 budget
- 234.6tok/s88.8OpenAI-compatible
- 331.5tok/s86.9llama.cpp k8 v4 -1 budgetthis run
Reproduce this run
toolllama.cpp k8 v4 -1 budget manual
modelQwen3.8-27B-Turbo-Brilliance-50X-RI-GSQ-RCO-IQ3_XXS-mtp
context65,536
thinkingon
clientv0.4.92+102
Set those in llama.cpp k8 v4 -1 budget, then:
llm-benchmark benchmark --model "Qwen3.8-27B-Turbo-Brilliance-50X-RI-GSQ-RCO-IQ3_XXS-mtp" --tool "llama.cpp k8 v4 -1 budget"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.