Benchmark result
google/gemma-4-e2b on NVIDIA GeForce RTX 3060 Laptop GPU — 105.5 tok/s
Measured with Bionic manual on October 12, 2026.
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 4 runs of this model on NVIDIA GeForce RTX 3060 Laptop GPU · median 105.3 tok/s.
sort
- 1106.2tok/s66.3Bionic
- 2105.5tok/s61.3Bionicthis run
- 3105.0tok/s63.5Bionic
- 4104.9tok/s58.6Bionic
Reproduce this run
toolBionic manual
modelgoogle/gemma-4-e2b
context32,768
clientv0.4.92+102
Set those in Bionic, then:
llm-benchmark benchmark --model "google/gemma-4-e2b" --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.