> For the complete documentation index, see [llms.txt](https://docs.roboflow.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.roboflow.com/deploy/self-hosted-deployment.md).

# Self-Hosted Deployment

You can deploy models and Workflows on your own hardware with Roboflow Inference, our edge inference server. This is ideal if you need your models to run in real time on the edge.

You will need an internet connection to set up a model on your hardware. You will also need a persistent internet connection if you are deploying models on devices managed by [Device Manager](/deploy/device-manager.md).

Refer to the [Roboflow Inference installation guide](https://inference.roboflow.com/install/) to learn how to set up Inference on your computer. Then, see our guide on [How to Deploy a Workflow](/workflows/deploy-a-workflow.md) on an edge device.

{% hint style="info" %}
TensorRT-optimized model packages for private models are only available on [Enterprise plans](/deploy/enterprise-deployment.md) when running Inference outside the Roboflow platform. Public models include TensorRT packages on all plans.
{% endhint %}