RedHatAI/Llama-3.1-8B-Instruct-NVFP4

Quantization vs meta-llama/Llama-3.1-8B-Instruct. RedHatAI/Llama-3.1-8B-Instruct-NVFP4 is a quantized version of the other (U8/BF16).

On the Hub · Downloads on Model Pulse