Benchmark result
Qwen3.8NextO on Apple M5 Max — 55.0 tok/s
Measured with oMLX 0.32.0 on September 26, 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
2nd fastest of 2 runs of this model on Apple M5 Max · median 58.2 tok/s.
sort
- 161.4tok/s84.3oMLX
- 255.0tok/s84.1oMLXthis run
Reproduce this run
tooloMLX 0.32.0
modelQwen3.8NextO
context262,144
samplingtemperature 1 · top_p 0.95 · top_k 20 · repetition_penalty 1.08
clientv0.4.80+98
Set those in oMLX, then:
llm-benchmark benchmark --model "Qwen3.8NextO" --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.