---
license: llama3.1
---

# Llama-3.1-Nemotron-70B-Reward-HF-INT4
4-bit version of the origninal model by Meta+Nvidia. 

This consumes about 52 GB VRAM. 

Please refer to the original license and documentation:

https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Reward-HF