Reference · How-to · ~8 min

How to run a local LLM with Ollama

Last updated Jul 17, 2026

Get an offline chat running in about 8 minutes.

Steps

1. Install Ollama from ollama.com

2. Pull a small model: `ollama pull llama3.2`

3. Run: `ollama run llama3.2`

4. Ask one factual question you can verify offline

5. Optional: hit `http://localhost:11434/api/chat` from your app

Local models are **smaller** — verify important facts. Check your org policy before running on work machines.

**Try the lesson:** `local-llms` in Lane C