mlx-community/granite-3.3-8b-instruct-4bit
Quantization vs ibm-granite/granite-3.3-8b-instruct. mlx-community/granite-3.3-8b-instruct-4bit is a quantized version of the other (U32/F16).
Quantization vs ibm-granite/granite-3.3-8b-instruct. mlx-community/granite-3.3-8b-instruct-4bit is a quantized version of the other (U32/F16).