Benchmark result
qwen3.8-4b-distill on AMD Radeon Vega Series / Radeon Vega Mobile Series — 10.7 tok/s
Measured with Bionic 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
3rd fastest of 4 runs of this model on AMD Radeon Vega Series / Radeon Vega Mobile Series · median 10.9 tok/s.
sort
- 111.4tok/s55.5Bionic
- 211.0tok/s54.0Bionic
- 310.7tok/s57.8Bionicthis run
- 46.4tok/s63.1Bionic
qwen3.8-4b-distill on other hardware
Reproduce this run
toolBionic manual
modelqwen3.8-4b-distill
context32,768
clientv0.4.99+102
Set those in Bionic, then:
llm-benchmark benchmark --model "qwen3.8-4b-distill" --tool "Bionic"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.