Benchmark result
Qwen3.8-27B-MTPLX-Optimized-Speed on Apple M5 Max — 52.7 tok/s
Measured with oMLX 0.7.0.dev4 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 51.5 tok/s.
sort
- 152.7tok/s86.7oMLX · KV nonethis run
- 250.3tok/s81.6oMLX · KV none
Reproduce this run
tooloMLX 0.7.0.dev4
modelQwen3.8-27B-MTPLX-Optimized-Speed
context65,536
kv cachenone
effortmedium
samplingtemperature 1 · top_p 0.95 · top_k 20 · min_p 0 · presence_penalty 1.5 · repetition_penalty 1
clientv0.4.80+98
Set those in oMLX, then:
llm-benchmark benchmark --model "Qwen3.8-27B-MTPLX-Optimized-Speed" --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.