Benchmark result
bonsai-2:4b on NVIDIA RTX 500 Ada Generation Laptop GPU — 48.0 tok/s
Measured with Ollama 0.40.11 on October 27, 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.
Reproduce this run
toolOllama 0.40.11
modelbonsai-2:4b (Q2_0)
context8,192
samplingtemperature 1 · top_p 0.95 · top_k 20 · presence_penalty 1
clientv0.4.98+102
Set those in Ollama, then:
llm-benchmark benchmark --model "bonsai-2:4b" --tool "Ollama"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.