# Running Crewai with NVLM-D-72B

**URL:** <https://community.crewai.com/t/running-crewai-with-nvlm-d-72b/1499>\
**Category:** General\
**Tags:** crewai\
**Created:** [November 19, 2024, 2:57am UTC](https://community.crewai.com/t/running-crewai-with-nvlm-d-72b/1499 "2024-11-19T02:57:40Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![glorianeo](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/glorianeo/32/1089_2.png) [@glorianeo](https://community.crewai.com/u/glorianeo)\
**Post date:** [November 19, 2024, 2:57am UTC](https://community.crewai.com/t/running-crewai-with-nvlm-d-72b/1499/1 "2024-11-19T02:57:40Z")

</div>

Hi, I would like to check if it is possible to run crewai with other models not listed in the documentation examples ([LLMs - CrewAI](https://docs.crewai.com/concepts/llms))?

I am keen to test my crewai pipeline on NVLM-D-72B locally.

---

<div class="post-metadata">

**Author:** ![rokbenko](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/rokbenko/32/492_2.png) [@rokbenko](https://community.crewai.com/u/rokbenko)\
**Post date:** [November 19, 2024, 11:07am UTC](https://community.crewai.com/t/running-crewai-with-nvlm-d-72b/1499/2 "2024-11-19T11:07:31Z")

</div>

@glorianeo Yes, it’s possible. CrewAI’s `LLM` class leverages LiteLLM in the background, which supports a wide range of [LLM providers](https://docs.litellm.ai/docs/providers). Among these is [Hugging Face](https://docs.litellm.ai/docs/providers/huggingface), enabling you to run models like [NVLM-D 72B](https://huggingface.co/nvidia/NVLM-D-72B).