Benchmark result
gemma-4-31B-it-MLX-8bit on Apple M2 Ultra — 16.6 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.
How this run compares
gemma-4-31B-it-MLX-8bit on other hardware
Reproduce this run
tooloMLX 0.31.3
modelgemma-4-31B-it-MLX-8bit
context262,144
thinkingon
clientv0.4.46+97
Set those in oMLX, then:
llm-benchmark benchmark --model "gemma-4-31B-it-MLX-8bit" --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.