mlx-community/Mellum2-12B-A2.5B-Instruct-mxfp4

Quantization vs JetBrains/Mellum2-12B-A2.5B-Instruct. mlx-community/Mellum2-12B-A2.5B-Instruct-mxfp4 is a quantized version of the other (U32/U8).

On the Hub · Downloads on Model Pulse