Benchmark result
MiMo-V2.6-Distill-Qwen-9B-oQ4e-fp16 on Apple M1 Pro — 33.1 tok/s
Measured with oMLX 0.7.0 on October 16, 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 2 runs of this model on Apple M1 Pro · median 32.2 tok/s.
sort
- 133.1tok/s62.4oMLX · FP16 · KV nonethis run
- 231.2tok/s65.4oMLX · FP16 · KV none
Reproduce this run
tooloMLX 0.7.0
modelMiMo-V2.6-Distill-Qwen-9B-oQ4e-fp16 (FP16)
context8,192
kv cachenone
think limitnone
samplingtemperature 1 · top_p 0.95 · top_k 0 · repetition_penalty 1
clientv0.4.96+102
Set those in oMLX, then:
llm-benchmark benchmark --model "MiMo-V2.6-Distill-Qwen-9B-oQ4e-fp16" --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.