Benchmark result
qwen3.8-27b on 2× AMD Radeon AI PRO R9700 — 79.3 tok/s
Measured with radiance manual on November 13, 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
1st fastest of 4 runs of this model on 2× AMD Radeon AI PRO R9700 · Multi-GPU · median 77.0 tok/s.
sort
- 179.3tok/s87.6radiancethis run
- 278.7tok/s87.6radiance
- 375.3tok/s90.1radiance
- 475.0tok/s85.3radiance
Reproduce this run
toolradiance manual
modelqwen3.8-27b
context65,536
clientv0.4.99+102
Set those in radiance, then:
llm-benchmark benchmark --model "qwen3.8-27b" --tool "radiance"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.