Benchmark result
Qwen3.8-27B-Uncensored-MLX on Apple M5 Max — 32.6 tok/s
Measured with oMLX 0.31.3 on August 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; 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 M5 Max · median 31.1 tok/s.
sort
- 132.6tok/s67.8oMLXthis run
- 229.6tok/s85.8oMLX
Reproduce this run
tooloMLX 0.31.3
modelQwen3.8-27B-Uncensored-MLX
context30,720
clientv0.4.42+97
Set those in oMLX, then:
llm-benchmark benchmark --model "Qwen3.8-27B-Uncensored-MLX" --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.