Benchmark result
gemma-4-12B-it-bf16 on Apple M2 Ultra — 24.0 tok/s
Measured with oMLX 0.31.3 on September 1, 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.
Reproduce this run
tooloMLX 0.31.3
modelgemma-4-12B-it-bf16
context131,072
thinkingon
clientv0.4.46+97
Set those in oMLX, then:
llm-benchmark benchmark --model "gemma-4-12B-it-bf16" --tool "oMLX"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.