Benchmark result
phi-3.1-mini-4k-instruct on NVIDIA GeForce RTX 3060 Laptop GPU — 77.1 tok/s
Measured with Bionic manual on October 14, 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 76.3 tok/s.
sort
- 178.1tok/s23.2Bionic
- 277.1tok/s—Bionicthis run
- 375.4tok/s30.6Bionic
- 474.0tok/s—Bionic
phi-3.1-mini-4k-instruct on other hardware
Reproduce this run
toolBionic manual
modelphi-3.1-mini-4k-instruct
context16,384
clientv0.4.92+102
Set those in Bionic, then:
llm-benchmark benchmark --model "phi-3.1-mini-4k-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.