Benchmark result
Qwen3.8-27B-IQ5R-V4-DFlash2-TP2-bf16KV on 2× AMD Radeon AI PRO R9700 — 123.0 tok/s
Measured with radiance manual on November 17, 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 2× AMD Radeon AI PRO R9700 · Multi-GPU · median 129.2 tok/s.
sort
- 1135.5tok/s85.6radiance
- 2123.0tok/s87.7radiancethis run
Reproduce this run
toolradiance manual
modelQwen3.8-27B-IQ5R-V4-DFlash2-TP2-bf16KV
context65,536
clientv0.4.99+102
Set those in radiance, then:
llm-benchmark benchmark --model "Qwen3.8-27B-IQ5R-V4-DFlash2-TP2-bf16KV" --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.