Qwen/Qwen3-0.6B-MLX-4bit

Quantization vs Qwen/Qwen3-0.6B-Base. Qwen/Qwen3-0.6B-MLX-4bit is a quantized version of the other (U32/BF16).

2 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse