Self-hosted Providers

This page will help you set up any self-hosted providers with LLM Vision

Ollama

To use Ollama you must set up an Ollama server first. You can download it from here. Once installed you need to download a model to use. A full list of all available models that support vision can be found here. Keep in mind that only models with vision capabilities can be used. The recommended model is gemma3.

ollama run gemma3

If your Home Assistant is not running on the same server as Ollama, you need to set the OLLAMA_HOST environment variable.

Linux

1. Edit the systemd service by calling systemctl edit ollama.service. This will open an editor.

2. For each environment variable, add a line Environment under section [Service]:

[Service]
Environment="OLLAMA_HOST=0.0.0.0"

1. Save and close the editor.

2. Reload systemd and restart Ollama

systemctl daemon-reload
systemctl restart ollama

Windows

1. Quit Ollama from the system tray

2. Open File Explorer

3. Right click on This PC and select Properties

4. Click on Advanced system settings

5. Select Environment Variables

6. Under User variables click New

7. For variable name enter OLLAMA_HOST and for value enter 0.0.0.0

8. Click OK and start Ollama again from the Start Menu

macOS

1. Open Terminal

2. Run the following command

launchctl setenv OLLAMA_HOST "0.0.0.0"

1. Restart Ollama

Models

See Ollama model library for all models.

Recommended Models

gemma3

qwen2.5vl

Open WebUI

Open WebUI is a self-hosted AI platform with a built-in inference engine for databases so you can add knowledge to your LLM which is also available in LLM Vision.

You will need to generate an API key in Settings > Account > JWT Token. In addition you also need to have at least one model (with vision support) added.

During setup you will need to provide:

• API key

• Model (model_id)

• IP address or hostname of your host

• Port (default is 3000)

LocalAI

To use LocalAI you need to have a LocalAI server running. You can find the installation instructions here. During setup you'll need to provide the IP address of your machine and port on which LocalAI is running (default is 8000). If you want to use HTTPS to send requests you need to check the HTTPS box.