Benchmark result
Ternary-Bonsai-2-27B-PQ2_0 on 2× NVIDIA GeForce RTX 5060 — 41.8 tok/s
Measured with llama.cpp b10709-9a9394a89 on September 21, 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 2 runs of this model on 2× NVIDIA GeForce RTX 5060 · Multi-GPU · median 41.6 tok/s.
- 141.8tok/s43.8llama.cpp · Q2_0this run
- 241.4tok/s78.5llama.cpp · Q2_0
Ternary-Bonsai-2-27B-PQ2_0 on other hardware
Reproduce this run
Set those in llama.cpp, then:
llm-benchmark benchmark --model "Ternary-Bonsai-2-27B-PQ2_0" --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.