Qwen

Qwen

Qwen/Qwen3-32B

Quantizations

Quant	Quantized by	Size	Decode	Prefill	Score	Actions
4bit	MLX Community MLX Community	17.2 GB	29.6 tok/s	255.3 tok/s	Runs ok	Run

Device Comparison

Results include trials with 4,096 input tokens and 1,024 output tokens only.