m1rkocasu/Apertus-v1.5-8B-text-MLX-8bit
Quantization vs swiss-ai/Apertus-v1.5-8B. m1rkocasu/Apertus-v1.5-8B-text-MLX-8bit is a quantized version of the other (U32/BF16).
2 other repos hold byte-for-byte identical weight files.
Quantization vs swiss-ai/Apertus-v1.5-8B. m1rkocasu/Apertus-v1.5-8B-text-MLX-8bit is a quantized version of the other (U32/BF16).
2 other repos hold byte-for-byte identical weight files.