Benchmark result
Ternary-Bonsai-2-9B-gguf-Q2_0 on NVIDIA GeForce RTX 2050 — 15.4 tok/s
Measured with Lemonade manual on November 20, 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
4th fastest of 4 runs of this model on NVIDIA GeForce RTX 2050 · median 15.7 tok/s.
sort
- 115.9tok/s67.3Lemonade · Q2_0
- 215.9tok/s58.7Lemonade · Q2_0
- 315.5tok/s58.6Lemonade · Q2_0
- 415.4tok/s51.1Lemonade · Q2_0this run
Ternary-Bonsai-2-9B-gguf-Q2_0 on other hardware
Reproduce this run
toolLemonade manual
modelTernary-Bonsai-2-9B-gguf-Q2_0 (Q2_0)
context65,536
thinkingoff
clientv0.4.99+102
Set those in Lemonade, then:
llm-benchmark benchmark --model "Ternary-Bonsai-2-9B-gguf-Q2_0" --tool "Lemonade"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.