appautomaton/granite-4.0-1b-speech-int8-mlx

Quantization vs ibm-granite/granite-4.0-1b-speech. appautomaton/granite-4.0-1b-speech-int8-mlx 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