Benchmark result
Qwen3.6-35B-A3B-Uncensored-Heretic-MLX-4bit on Apple M4 Pro — 101.5 tok/s
Measured with oMLX manual on November 4, 2026.
Support llm-bench.io
llm-bench.io is free. If it helped you, I'd appreciate your support to cover the infrastructure costs.
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
7th fastest of 10 runs of this model on Apple M4 Pro · median 110.2 tok/s.
sort
Compare the nearest 5 →
Reproduce this run
tooloMLX manual
modelQwen3.6-35B-A3B-Uncensored-Heretic-MLX-4bit
context262,144
clientv0.4.98+102
Set those in oMLX, then:
llm-benchmark benchmark --model "Qwen3.6-35B-A3B-Uncensored-Heretic-MLX-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.