RedHatAI/granite-3.1-8b-base-quantized.w4a16
Quantization vs ibm-granite/granite-3.1-8b-base. RedHatAI/granite-3.1-8b-base-quantized.w4a16 is a quantized version of the other (I32/BF16).
Quantization vs ibm-granite/granite-3.1-8b-base. RedHatAI/granite-3.1-8b-base-quantized.w4a16 is a quantized version of the other (I32/BF16).