FriendliAI/Meta-Llama-3.1-8B-Instruct-int8

Quantization vs meta-llama/Llama-3.1-8B. FriendliAI/Meta-Llama-3.1-8B-Instruct-int8 is a quantized version of the other (I8/BF16).

On the Hub · Downloads on Model Pulse