RedHatAI/Llama-3.1-Nemotron-70B-Instruct-HF-FP8-dynamic
Quantization vs nvidia/Llama-3.1-Nemotron-70B-Instruct-HF. RedHatAI/Llama-3.1-Nemotron-70B-Instruct-HF-FP8-dynamic is a quantized version of the other (F8_E4M3/BF16).
2 other repos hold byte-for-byte identical weight files.