> For the complete documentation index, see [llms.txt](https://docs.degirum.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.degirum.com/hailo/advanced-guides/ai-server.md).

# AI Server

Learn how to use the DeGirum AI Server to efficiently host your hardware with local or cloud models.

*Estimated read time: 4 minutes*

You should use the DeGirum AI server when you want to:

* Use models from the DeGirum AI Hub while running inference on local Hailo accelerators.
* Serve models from on-device storage for fully offline or LAN-hosted operation.

{% hint style="info" %}
If you want to set `HAILO_MONITOR=1` and you plan to use an AI Server started as a service, add `Environment="HAILO_MONITOR=1"` under `[Service]` in `/etc/systemd/system/degirum.service`, then reload the daemon.
{% endhint %}

Continue to [Inference with cloud models](/hailo/advanced-guides/ai-server/ai-server-inference-with-cloud-models.md) or [Inference with local models](/hailo/advanced-guides/ai-server/ai-server-inference-with-local-models.md) to learn more about using a DeGirum AI server.