Benchmark result
prism-ml/Ternary-Bonsai-2-27B-gguf on NVIDIA GeForce RTX 4070 — 46.4 tok/s
Measured with Unsloth Studio on September 27, 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.
How this run compares
2nd fastest of 3 runs of this model on NVIDIA GeForce RTX 4070 · median 46.4 tok/s.
sort
- 147.9tok/s40.8Unsloth Studio · KV f16
- 246.4tok/s53.4Unsloth Studio · TQ1_0 · KV f16this run
- 345.1tok/s72.7Unsloth Studio · TQ1_0 · KV f16
Reproduce this run
toolUnsloth Studio
modelprism-ml/Ternary-Bonsai-2-27B-gguf (TQ1_0)
context16,384
kv cachef16
thinkingon
effortxhigh (model default)
samplingtemperature 0.7 · top_p 0.95 · top_k -1 · min_p 0.01 · presence_penalty 0
clientv0.4.80+98
Set those in Unsloth Studio, then:
llm-benchmark benchmark --model "prism-ml/Ternary-Bonsai-2-27B-gguf" --tool "Unsloth 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.