mlx-community/VibeThinker-1.5B-mlx-4bit

Quantization vs WeiboAI/VibeThinker-1.5B. mlx-community/VibeThinker-1.5B-mlx-4bit 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