Qwen

Qwen

Qwen/Qwen3-0.6B

Quantizations

Quant	Quantized by	Size	Decode	Prefill	Score	Actions
4bit	MLX Community MLX Community	319.9 MB	154.6 tok/s	1,991.0 tok/s	Runs great	Run
q8_0	Unsloth Unsloth	609.8 MB	108.9 tok/s	2,757.2 tok/s	Runs great	Run

Device Comparison

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