Benchmark result
qwen3.8-27b on AMD Radeon RX 7800 XT — 56.7 tok/s
Measured with yasakani-hip-think manual on November 16, 2026.
Support llm-bench.io
llm-bench.io is free. If it helped you, I'd appreciate your support to cover the infrastructure costs.
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
2nd fastest of 2 runs of this model on AMD Radeon RX 7800 XT · median 59.6 tok/s.
sort
- 162.6tok/s72.2yasakani-hip-greedy
- 256.7tok/s81.3yasakani-hip-thinkthis run
Reproduce this run
toolyasakani-hip-think manual
modelqwen3.8-27b
context8,192
thinkingon
clientv0.4.99+102
Set those in yasakani-hip-think, then:
llm-benchmark benchmark --model "qwen3.8-27b" --tool "yasakani-hip-think"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.