# LLAMA-2 Multi-Node

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fllama-2-multi-node%2F50004%3E%5C
**Category:** Models\
**Created:** [August 8, 2023, 6:05pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fllama-2-multi-node%2F50004 "2023-08-08T18:05:31Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![rajat-saxena](https://avatars.discourse-cdn.com/v4/letter/r/b5ac83/32.png) [@rajat-saxena](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Frajat-saxena)%5C
**Post date:** [August 8, 2023, 6:05pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fllama-2-multi-node%2F50004%2F1 "2023-08-08T18:05:31Z")

</div>

Will LLAMA-2 benefit from using multiple nodes (each with one GPU) for inference?

Are there any examples of LLAMA-2 on multiple nodes for inference?