Benchmark result
prism-ml/Ternary-Bonsai-2-4B-gguf on Intel(R) Arc(TM) 140V GPU (16GB) — 40.2 tok/s
Measured with Unsloth Studio on October 23, 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.
How this run compares
2nd fastest of 3 runs of this model on Intel(R) Arc(TM) 140V GPU (16GB) · median 40.2 tok/s.
sort
- 140.2tok/s58.8Unsloth Studio · Q2_0 · KV q4_0
- 240.2tok/s57.7Unsloth Studio · Q2_0 · KV q8_0this run
- 338.5tok/s54.5Unsloth Studio · Q2_0 · KV q8_0
prism-ml/Ternary-Bonsai-2-4B-gguf on other hardware
Reproduce this run
toolUnsloth Studio
modelprism-ml/Ternary-Bonsai-2-4B-gguf (Q2_0)
context262,144
kv cacheq8_0
thinkingon
effortmedium
think limitnone
samplingtemperature 0.7 · top_p 0.95 · top_k -1 · min_p 0.01 · presence_penalty 0
clientv0.4.97+102
Set those in Unsloth Studio, then:
llm-benchmark benchmark --model "prism-ml/Ternary-Bonsai-2-4B-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.