Local AI Local AI Foundations

Pull and Run Your First Model

Use ollama run for quick terminal chat

56 of 66

Interactive chat

Run a model in chat mode:

ollama run llama3.2

Type prompts and press Enter. Type

/bye

to exit.

One-shot prompts

For single questions, pass the prompt as an argument:

ollama run llama3.2 "Explain this regex: ^[a-z]+$"

List installed models

ollama list

Remove a model

ollama rm llama3.2

Try different sizes

Ollama supports tags for model variants:

ollama pull llama3.2:1b   # tiny, fast
ollama pull llama3.2      # default 3B
ollama pull llama3.1:8b   # larger, smarter

Pick the smallest model that solves your task.

Working out which model to run this on? See The Codex. Packaging it as a reusable skill? See The Armory.