Help Center › Your AI

Local AI with Ollama (advanced)

If you’d rather nothing leave your computer at all, point Tentaku at a model running locally. Tentaku sends each prompt to your command on standard input and reads the reply from standard output.

1. Install Ollama from ollama.com and download a model, for example ollama pull llama3.
2. In Tentaku: Settings → Your AI → choose “Local AI — custom command (Ollama and similar)”.
3. Enter the command, for example ollama run llama3, then Save → Test.

With Local AI, nothing leaves your computer from Tentaku. Local models are slower than hosted ones and need a capable machine; notes may be thinner.

Still stuck? Email [email protected] — include which tab you were on and what you pressed.