A short, practical guide to running a language model locally on your own machine with Ollama — no cloud required.
Difficultybeginner
Est. time15 minutes
Prerequisites
- A machine with enough RAM
- Internet to download
Steps
- Install Ollama from ollama.com
- Run: ollama run llama3.1
- Wait for the model to download
- Chat in the terminal
- Use the local API on port 11434
Tools
- Ollama
Models
- llama3.1
- mistral
