Ollama Guide

Ollama runs open-source models on a computer or server and exposes an OpenAI-compatible API that 3sparks Chat can use.

Set up Ollama

1. Install Ollama from ollama.com.
2. Download a model, for example ollama pull llama3.2.
3. Start Ollama and confirm it is reachable on port 11434.
4. Find the LAN IP or Tailscale IP of the computer running Ollama.

Add the connection

1. Open 3sparks Chat and go to Connections.
2. Tap + and choose Ollama.
3. Leave the name blank for a generated name, or enter your own.
4. Set the base URL to http://YOUR_LOCAL_IP:11434.
5. Tap Create Connection.
6. Tap Fetch Models, choose a default model, and tap Done.

Troubleshooting

• Do not use localhost from iPhone or iPad; use the computer's LAN IP or Tailscale IP.
• Confirm Ollama is running and the model has been pulled.
• If models do not appear, make sure Ollama is listening on a network interface reachable by your device.
• Lower token limits for small models if long prompts fail.