nvidia/Llama-3.3-70B-Instruct-NVFP4

Quantization vs meta-llama/Llama-3.3-70B-Instruct. nvidia/Llama-3.3-70B-Instruct-NVFP4 is a quantized version of the other (U8/F8_E4M3).

1 derivatives checked

• nvidia/Llama-3.3-70B-Instruct-Eagle3: Quantization

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

On the Hub · Downloads on Model Pulse