Benchmark result
bonsai-2:27b on AMD Radeon RX 9060 XT +1 more — 25.8 tok/s
Measured with Ollama 0.40.6 on October 25, 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
bonsai-2:27b on other hardware
Reproduce this run
toolOllama 0.40.6
modelbonsai-2:27b (Q2_0)
context65,536
samplingtemperature 1 · top_p 0.95 · top_k 20 · min_p 0.05
clientv0.4.98+102
Set those in Ollama, then:
llm-benchmark benchmark --model "bonsai-2:27b" --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.