ibm-granite/granite-4.0-h-small-FP8
Quantization vs ibm-granite/granite-4.0-h-small. ibm-granite/granite-4.0-h-small-FP8 is a quantized version of the other (F8_E4M3/BF16).
1 other repos hold byte-for-byte identical weight files.
Quantization vs ibm-granite/granite-4.0-h-small. ibm-granite/granite-4.0-h-small-FP8 is a quantized version of the other (F8_E4M3/BF16).
1 other repos hold byte-for-byte identical weight files.