Benchmark result
phi-4-mini-instruct on NVIDIA GeForce RTX 3060 Laptop GPU — 86.4 tok/s
Measured with Bionic manual on November 15, 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
1st fastest of 4 runs of this model on NVIDIA GeForce RTX 3060 Laptop GPU · median 85.9 tok/s.
sort
- 186.4tok/s28.1Bionicthis run
- 286.1tok/s28.0Bionic
- 385.7tok/s32.5Bionic
- 484.3tok/s25.5Bionic
Reproduce this run
toolBionic manual
modelphi-4-mini-instruct
context16,384
clientv0.4.98+102
Set those in Bionic, then:
llm-benchmark benchmark --model "phi-4-mini-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.