Infermatic/Llama-3.3-70B-Instruct-FP8-Dynamic

Quantization vs meta-llama/Llama-3.1-70B. Infermatic/Llama-3.3-70B-Instruct-FP8-Dynamic is a quantized version of the other (F8_E4M3/BF16).

5 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse