Benchmark result
Ternary-Bonsai-2-27B-Q2_0-prism-fork-required on 2× NVIDIA GeForce RTX 5060 — 38.4 tok/s
Measured with llama.cpp b11557-5c8854fd8 on October 11, 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
toolllama.cpp b11557-5c8854fd8
modelTernary-Bonsai-2-27B-Q2_0-prism-fork-required (Q2_0)
context147,456
thinkingon
think limit32,768 tokens
samplingtemperature 0.6000000238418579 · top_p 0.800000011920929 · top_k 20 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1.0499999523162842
clientv0.4.92+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "Ternary-Bonsai-2-27B-Q2_0-prism-fork-required" --tool "llama.cpp"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.