RedHatAI/Mistral-Small-24B-Instruct-2501-FP8-dynamic
Quantization vs mistralai/Mistral-Small-24B-Instruct-2501. RedHatAI/Mistral-Small-24B-Instruct-2501-FP8-dynamic is a quantized version of the other (F8_E4M3/BF16).
2 other repos hold byte-for-byte identical weight files.