lmstudio-community/ERNIE-4.5-21B-A3B-MLX-4bit

Quantization vs baidu/ERNIE-4.5-21B-A3B-PT. lmstudio-community/ERNIE-4.5-21B-A3B-MLX-4bit is a quantized version of the other (U32/BF16).

On the Hub · Downloads on Model Pulse