Benchmark result
Muse-Glimmer-30B-4bit on Apple M5 Max — 31.1 tok/s
Measured with oMLX 0.31.4.dev132+g94cdcae13 on October 14, 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
1st fastest of 4 runs of this model on Apple M5 Max · median 30.3 tok/s.
sort
- 131.1tok/s81.6oMLX · 4bit · KV nonethis run
- 230.7tok/s80.5oMLX
- 329.9tok/s85.3oMLX
- 429.1tok/s80.4oMLX
Reproduce this run
tooloMLX 0.31.4.dev132+g94cdcae13
modelMuse-Glimmer-30B-4bit (4bit)
context131,072
kv cachenone
thinkingoff
samplingtemperature 1 · top_p 0.95 · top_k 20 · repetition_penalty 1
clientv0.4.85+101
Set those in oMLX, then:
llm-benchmark benchmark --model "Muse-Glimmer-30B-4bit" --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.