Benchmark result
granite-4.2-30b-MLX-8bit on Apple M5 Max — 16.1 tok/s
Measured with oMLX 0.31.3 on September 24, 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
1st fastest of 2 runs of this model on Apple M5 Max · median 16.0 tok/s.
sort
- 116.1tok/s71.0oMLX · 8bit · KV nonethis run
- 215.9tok/s73.3oMLX · 8bit · KV none
Reproduce this run
tooloMLX 0.31.3
modelgranite-4.2-30b-MLX-8bit (8bit)
context131,072
kv cachenone
thinkingon
samplingtemperature 1 · top_p 0.95 · top_k 20 · repetition_penalty 1
clientv0.4.80+98
Set those in oMLX, then:
llm-benchmark benchmark --model "granite-4.2-30b-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.