Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.lmsa.app/llms.txt

Use this file to discover all available pages before exploring further.

Ollama is an open-source tool that makes it easy to download and run large language models on your own computer. It exposes a local HTTP server that LMSA can connect to over your Wi-Fi network, keeping your conversations entirely on your local network.

​
Before you start

Both your PC and your Android device must be connected to the same Wi-Fi network. LMSA communicates with Ollama over your local network, so this is required.

​
Set up Ollama on your PC

1

Install Ollama

Download and install Ollama from ollama.com on your Windows, macOS, or Linux computer.
2

Configure Ollama to accept network connections

By default, Ollama only listens on localhost, which means your Android device cannot reach it. You need to set the OLLAMA_HOST environment variable to allow connections from other devices on your network.
  • Windows: Open System Properties → Environment Variables and add a new system variable OLLAMA_HOST with the value 0.0.0.0.
  • macOS: Add the following line to your shell profile (~/.zshrc or ~/.bash_profile) and restart your terminal: 
    export OLLAMA_HOST=0.0.0.0
  • Linux (systemd): Edit the Ollama service override: 
    sudo systemctl edit ollama
    Add: 
    [Service]
Environment="OLLAMA_HOST=0.0.0.0"
    Then run sudo systemctl restart ollama.
After changing this setting, restart Ollama.
3

Pull a model

Open a terminal and pull a model. For example:
ollama pull llama3
You can browse available models at ollama.com/library.
4

Find your PC's local IP address

You need the PC’s local network IP address — not localhost or 127.0.0.1.
  • Windows: Open a terminal and run ipconfig. Look for the IPv4 Address under your Wi-Fi adapter (for example, 192.168.1.45).
  • macOS: Open System Settings → Wi-Fi → Details and copy the IP Address field.
  • Linux: Run ip addr show and look for your Wi-Fi interface’s inet address.
If you skip the OLLAMA_HOST=0.0.0.0 step, Ollama will only be reachable from localhost on your PC. LMSA will not be able to connect from your Android device.

​
Connect LMSA to Ollama

1

Open Settings in LMSA

Tap the settings icon in the top-right corner of the LMSA home screen.
2

Select Local Server

On the Connection step, tap Local Server.
3

Enable Ollama mode

Tap Configure and turn on the Ollama toggle. This switches LMSA to Ollama’s API format, which is required for correct model discovery and chat.
4

Enter your PC's IP and port

Enter your PC’s local IP address (for example, 192.168.1.45) and port 11434 (Ollama’s default port). Tap Save.
5

Start chatting

LMSA will load the list of available Ollama models. Select a model from the model picker and start chatting.
When Ollama mode is enabled, LMSA automatically uses Ollama’s OpenAI-compatible API at /v1/chat/completions. You do not need to configure this manually.

​
Troubleshooting

  • Confirm that you set OLLAMA_HOST=0.0.0.0 and restarted Ollama after making the change.
  • Make sure both devices are on the same Wi-Fi network.
  • Verify that port 11434 is not blocked by a firewall on your PC.
  • You can test from another terminal on your PC with: curl http://localhost:11434/api/tags — if this returns a model list, Ollama is running correctly.
At least one model must be pulled before LMSA can list them. Run ollama pull <model-name> and then refresh the connection in LMSA settings.
LMSA detects the currently running Ollama model automatically. If no model is actively running, select one from the model picker in LMSA to load it.
Use LMSA’s Saved Presets feature in the Connection settings panel to save your Ollama server details. This lets you switch between multiple server configurations quickly if you run Ollama on more than one machine.