ibm-granite/granite-3.3-8b-instruct-FP8
Quantization vs ibm-granite/granite-3.3-8b-instruct. ibm-granite/granite-3.3-8b-instruct-FP8 is a quantized version of the other (F8_E4M3/BF16).
Quantization vs ibm-granite/granite-3.3-8b-instruct. ibm-granite/granite-3.3-8b-instruct-FP8 is a quantized version of the other (F8_E4M3/BF16).