Your first local chat

Free
0/7 steps visited

Step 1 of 7

What we're doing

Intro · ~3 min

What we're doing

Lesson 3 — Your first local chat.

Ollama's installed from Lesson 2, and your model tag is on a sticky from Lesson 1. Today you do the three things that make it real: download the weights, talk to them, and prove they're on your disk.

This is the lesson people screenshot.

By the end (~50 minutes)

  • Your starter model pulled (ollama pull).
  • The Example Ink prompt answered in your terminal — no login, no subscription screen.
  • ollama list showing your model.
  • The checkpoint passed.

Before you start

  • Required: Lesson 2 checkpoint — Ollama running.
  • Your model tag from Lesson 1 — you'll paste the pull command for your choice.
  • Time: the first pull can take 5–20 minutes on home broadband. Get a brew on.

It's the same Example Ink prompt as the comparison lab, and that's on purpose. When the reply lands in your terminal, pause for a second — that one never left your building.

Continue — pull your model.

Warning

Real power. Educational use only.

What we teach you to build is genuinely powerful — uncensored assistants, agents, and automations on your own hardware. In the wrong hands, that is as dangerous as malicious code in the wrong hands. We do not teach illegal, malicious, or harmful use. You are responsible for what you deploy.

See what we mean →