Run an Llm on Your Laptop for Free with Ollama

This guide teaches you how to install Ollama and chat with a real AI model that runs entirely on your laptop. You will produce a local AI chat setup for drafting, summarizing, and brainstorming, with no account, subscription, or cloud processing required. The source frames this as a lightweight setup you can get installed tonight.

• Consultants and agency owners who handle client information they do not want sent to a third-party server.
• Marketers, writers, and operators who want to iterate on prompts without watching a usage meter.
• Anyone curious about local AI who does not want to sign up for another subscription just to try it.

You will build a working local AI chat setup using the Ollama desktop app. The model lives on your hard drive, runs on your CPU or GPU, and works offline once it has downloaded.

• A reasonably modern laptop running Mac, Windows, or Linux.
• At least 8 GB of RAM is ideal, though 4 GB works with a smaller model.
• At least 3 to 8 GB of free disk space, depending on the model you pick.
• No account or subscription is required.

• Wire up a coding agent. Ollama can launch Claude Code, Codex, or OpenCode against the model you downloaded using ollama launch claude, ollama launch codex, or ollama launch opencode.
• Give your model tools and web search. Ollama exposes a local API at http://localhost:11434 and supports tool calling, so you can connect it to web search, file readers, and other utilities.
• Move it to a dedicated machine. An old Mac mini, a recent used M-series Mac mini, or a repurposed PC can become an always-on local AI box that other devices on your home network can reach.