Benchmark result
Qwen3.6:35B-4bit on Apple M5 Max — 25.7 tok/s
Measured with oMLX 0.31.3 on July 15, 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
2nd fastest of 2 runs of this model on Apple M5 Max · median 64.6 tok/s.
sort
- 1103.4tok/s79.5oMLX
- 225.7tok/s82.2oMLXthis run
Reproduce this run
tooloMLX 0.31.3
modelQwen3.6:35B-4bit
context65,536
clientv0.4.28+97
Set those in oMLX, then:
llm-benchmark benchmark --model "Qwen3.6:35B-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.