Benchmark result
granite-3.3-8b-instruct on NVIDIA GeForce RTX 3060 Laptop GPU — 14.1 tok/s
Measured with Bionic manual on October 26, 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
1st fastest of 3 runs of this model on NVIDIA GeForce RTX 3060 Laptop GPU · median 13.4 tok/s.
sort
- 114.1tok/s49.0Bionicthis run
- 213.4tok/s47.7Bionic
- 313.3tok/s52.9Bionic
Reproduce this run
toolBionic manual
modelgranite-3.3-8b-instruct
context16,384
clientv0.4.96+102
Set those in Bionic, then:
llm-benchmark benchmark --model "granite-3.3-8b-instruct" --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.