Benchmark result
ministral-3-3b-instruct-2512 on AMD Radeon Vega Series / Radeon Vega Mobile Series — 13.1 tok/s
Measured with Bionic manual on October 31, 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 13.1 tok/s.
- 113.6tok/s52.7Bionic
- 213.1tok/s59.7Bionic
- 313.1tok/s49.5Bionicthis run
- 412.6tok/s39.8Bionic
ministral-3-3b-instruct-2512 on other hardware
Reproduce this run
Set those in Bionic, then:
llm-benchmark benchmark --model "ministral-3-3b-instruct-2512" --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.