Benchmark result
gemma-3-4b-it on AMD Radeon Vega Series / Radeon Vega Mobile Series — 12.6 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
4th fastest of 5 runs of this model on AMD Radeon Vega Series / Radeon Vega Mobile Series · median 12.7 tok/s.
sort
- 112.9tok/s54.7Bionic
- 212.7tok/s46.8Bionic
- 312.7tok/s44.9Bionic
- 412.6tok/s44.5Bionicthis run
- 512.4tok/s51.0Bionic
Reproduce this run
toolBionic manual
modelgemma-3-4b-it
context65,536
clientv0.4.98+102
Set those in Bionic, then:
llm-benchmark benchmark --model "gemma-3-4b-it" --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.