# LLAMA-2 Multi-Node

**URL:** <https://discuss.huggingface.co/t/llama-2-multi-node/50004>\
**Category:** Models\
**Created:** [August 8, 2023, 6:05pm UTC](https://discuss.huggingface.co/t/llama-2-multi-node/50004 "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](https://discuss.huggingface.co/u/rajat-saxena)\
**Post date:** [August 8, 2023, 6:05pm UTC](https://discuss.huggingface.co/t/llama-2-multi-node/50004/1 "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?