ibm-granite/granite-4.1-3b-fp8
Quantization vs ibm-granite/granite-4.1-3b. ibm-granite/granite-4.1-3b-fp8 is a quantized version of the other (F8_E4M3/BF16).
Quantization vs ibm-granite/granite-4.1-3b. ibm-granite/granite-4.1-3b-fp8 is a quantized version of the other (F8_E4M3/BF16).