NousResearch/Hermes-3-Llama-3.1-70B-FP8

Quantization vs meta-llama/Llama-3.1-70B. NousResearch/Hermes-3-Llama-3.1-70B-FP8 is a quantized version of the other (F8_E4M3/F16).

On the Hub · Downloads on Model Pulse