Benchmark result
qwen3.8-2b-distill on NVIDIA GeForce RTX 3060 Laptop GPU — 40.1 tok/s
Measured with Bionic manual on October 12, 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
5th fastest of 6 runs of this model on NVIDIA GeForce RTX 3060 Laptop GPU · median 110.9 tok/s.
sort
- 1115.6tok/s24.9Bionic
- 2114.5tok/s25.4Bionic
- 3112.5tok/s28.6Bionic
- 4109.4tok/s30.9Bionic
- 540.1tok/s30.3Bionicthis run
- 638.2tok/s29.4Bionic
Reproduce this run
toolBionic manual
modelqwen3.8-2b-distill
context8,192
clientv0.4.92+102
Set those in Bionic, then:
llm-benchmark benchmark --model "qwen3.8-2b-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.