> ## Documentation Index
> Fetch the complete documentation index at: https://docs.levelrail.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Self-host Text Generation Inference with Docker

> Hugging Face's production inference server for transformer language models, with continuous batching and streaming.

Hugging Face's production inference server for transformer language models, with continuous batching and streaming.

This page describes the Levelrail template for Text Generation Inference (AI). It deploys the services below as one Docker Compose app on your own server. Project site: [https://huggingface.co/docs/text-generation-inference](https://huggingface.co/docs/text-generation-inference).

Recommended memory: about 8192 MiB.

<Warning>This template reserves an NVIDIA GPU, so it needs a node with a GPU and the NVIDIA container runtime.</Warning>

## Services, ports and volumes

| Service | Image | Container ports | Volumes |
| - | - | - | - |
| `tgi` | `ghcr.io/huggingface/text-generation-inference:3.3.6` | 80 | `tgi_data -&#62; /data` |

## Environment variables

This template sets no environment variables.

Passwords and keys marked as generated are created for you when the app is deployed and stored as secrets. Values are not shown here.

## Deploy Text Generation Inference with Levelrail

In the dashboard, open **Apps**, choose **New app**, then **Browse templates**, and select Text Generation Inference. Review the Compose body and deploy.

With the CLI:

```bash theme={"dark"}
levelrail-cli templates deploy text-generation-inference --name my-text-generation-inference
```

See the [service template catalog](/templates-and-registry) for how templates work, and [Getting started](/getting-started) if you have not installed Levelrail yet.

## More AI templates

* [AnythingLLM](/self-host/anythingllm)
* [ComfyUI](/self-host/comfyui)
* [Flowise](/self-host/flowise)
* [Flowise (Postgres + Qdrant)](/self-host/flowise-postgres)
* [Jupyter GPU Notebook](/self-host/jupyter-gpu)

All templates are listed in the [self-host gallery](/self-host).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.