m1rkocasu/Apertus-v1.5-8B-text-MLX-6bit

Quantization vs swiss-ai/Apertus-v1.5-8B. m1rkocasu/Apertus-v1.5-8B-text-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