# Are there any LLMs that can run with decent performance on hardware comparable to Jetson NX?

**URL:** <https://discuss.huggingface.co/t/are-there-any-llms-that-can-run-with-decent-performance-on-hardware-comparable-to-jetson-nx/174305>\
**Category:** Models\
**Created:** [March 16, 2026, 6:09am UTC](https://discuss.huggingface.co/t/are-there-any-llms-that-can-run-with-decent-performance-on-hardware-comparable-to-jetson-nx/174305 "2026-03-16T06:09:49Z")\
**Posts on this page:** 1\
**Showing post:** 3

<div class="post-metadata">

**Author:** ![roroep](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/roroep/32/58533_2.png) [@roroep](https://discuss.huggingface.co/u/roroep)\
**Post date:** [March 16, 2026, 6:40am UTC](https://discuss.huggingface.co/t/are-there-any-llms-that-can-run-with-decent-performance-on-hardware-comparable-to-jetson-nx/174305/3 "2026-03-16T06:40:46Z")

</div>

Hello, I think we can help you about the memory bottleneck.

Please check the [post](https://discuss.huggingface.co/t/running-8b-llama-on-jetson-orin-nano-using-only-2-5gb-of-gpu-memory/174180) I uploaded on the forum last week. If you are interested, please give us a message via our homepage. We would like to discuss details!

---

_[View the full topic](https://discuss.huggingface.co/t/are-there-any-llms-that-can-run-with-decent-performance-on-hardware-comparable-to-jetson-nx/174305)._