Benchmark result
ternary-bonsai-2-27b on 2× NVIDIA GeForce RTX 4070 — 28.1 tok/s
Measured with LM Studio manual on October 1, 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
ternary-bonsai-2-27b on other hardware
Reproduce this run
toolLM Studio manual
modelternary-bonsai-2-27b
context65,536
thinkingon
clientv0.4.85+101
Set those in LM Studio, then:
llm-benchmark benchmark --model "ternary-bonsai-2-27b" --tool "LM Studio"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.