lmstudio-community/Qwen3-4B-Instruct-2507-MLX-6bit

Quantization vs Qwen/Qwen3-4B-Instruct-2507. lmstudio-community/Qwen3-4B-Instruct-2507-MLX-6bit is a quantized version of the other (U32/BF16).

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

On the Hub · Downloads on Model Pulse