# NVIDI LLaVA VILA models

**URL:** <https://forums.developer.nvidia.com/t/nvidi-llava-vila-models/336906>\
**Category:** Jetson Orin Nano\
**Tags:** generative\_ai\
**Created:** [June 23, 2025, 7:06am UTC](https://forums.developer.nvidia.com/t/nvidi-llava-vila-models/336906 "2025-06-23T07:06:41Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![joshkimchi](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@joshkimchi](https://forums.developer.nvidia.com/u/joshkimchi)\
**Post date:** [June 23, 2025, 7:06am UTC](https://forums.developer.nvidia.com/t/nvidi-llava-vila-models/336906/1 "2025-06-23T07:06:41Z")

</div>

I am running the VILA1.5-3b but when I run the video query script, it is unable to do so as I do not have the local\_llm. does anyone know where I should be finding this from GitHub to clone? it seems like I can’t find the right one to make my script work. Thanks

---

<div class="post-metadata">

**Author:** ![AastaLLL](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/aastalll/32/14043_2.png) [@AastaLLL](https://forums.developer.nvidia.com/u/AastaLLL)\
**Post date:** [June 24, 2025, 2:48am UTC](https://forums.developer.nvidia.com/t/nvidi-llava-vila-models/336906/3 "2025-06-24T02:48:45Z")

</div>

Hi,

You can find some samples in the page below:

> **[Models | Jetson AI Lab](https://www.jetson-ai-lab.com/models.html/)**
>
> Discover all generative AI models optimized for Jetson

Thanks.

---

<div class="post-metadata">

**Author:** ![joshkimchi](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@joshkimchi](https://forums.developer.nvidia.com/u/joshkimchi)\
**Post date:** [June 24, 2025, 2:56am UTC](https://forums.developer.nvidia.com/t/nvidi-llava-vila-models/336906/4 "2025-06-24T02:56:23Z")

</div>

Hello, thank you for the reply, I am running a VILA 1.5-3b model on the Jetson Orin Nano, im currently trying to use @dusty_nv 's code in his Live LLaVA demo but that does not seem to be working, with the issue of the llm module not being found.

---

<div class="post-metadata">

**Author:** ![AastaLLL](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/aastalll/32/14043_2.png) [@AastaLLL](https://forums.developer.nvidia.com/u/AastaLLL)\
**Post date:** [June 25, 2025, 7:12am UTC](https://forums.developer.nvidia.com/t/nvidi-llava-vila-models/336906/5 "2025-06-25T07:12:26Z")

</div>

Hi,

For VILA, have you tried the server.py included in this container image: dustynv/vila:r36.4.0-cu128-24.04?

We use the chat.completion microservice interface for LLM/VLM now instead of library-level access in NanoLLM from projects like vLLM and SGLang that keep up with VLM releases.

Thanks.

---

<div class="post-metadata">

**Author:** ![system](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/system/32/68080_2.png) [@system](https://forums.developer.nvidia.com/u/system)\
**Post date:** [July 16, 2025, 2:35am UTC](https://forums.developer.nvidia.com/t/nvidi-llava-vila-models/336906/7 "2025-07-16T02:35:56Z")

</div>

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.