Benchmark result
Qwen3.8-27B-Turbo-Brilliance-50X-RI-GSQ-RCO-IQ3_S-mtp on AMD Radeon RX 7800 XT — 33.7 tok/s
Measured with llama.cpp k8 v4 -1 budget 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.
How this run compares
1st fastest of 2 runs of this model on AMD Radeon RX 7800 XT · median 33.7 tok/s.
sort
- 133.7tok/s86.1llama.cpp k8 v4 -1 budgetthis run
- 233.6tok/s82.6llama.cpp k8 v4 -1 budget
Reproduce this run
toolllama.cpp k8 v4 -1 budget manual
modelQwen3.8-27B-Turbo-Brilliance-50X-RI-GSQ-RCO-IQ3_S-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_S-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.