Local AI

Run your own models at home: Ollama, LM Studio, Open WebUI, llama.cpp — no cloud, no API key, your data stays yours.

Local AI means the model runs on your machine. Slower than the biggest cloud models, but private, free per request, and it works offline. These tutorials get you from zero to a chat interface running locally.

Ollama: run LLMs locally in 3 commands

Install Ollama, pull a model, and chat — from the terminal and from any app, over a local API. Tested on a real Windows machine.

llama.cpp: the engine that runs local AI

Download the official Windows build, load a GGUF model, serve it over the OpenAI API — and measure the speed. Tested on a real CPU-only machine.

Open WebUI: a ChatGPT-style interface for your local models

Install Open WebUI without Docker (the uv path), create your account, and chat with the models you already pulled in Ollama. Tested end-to-end on a real machine.

LM Studio: the full local AI workstation — hub, chat, server, CLI

Install LM Studio, download a model from the Hub, chat in the app, and serve it with the local OpenAI-compatible API on port 1234. Plus the lms CLI that does it all from the terminal.

Hermes Agent: a local AI agent that actually works on your machine

Install Hermes Agent, point it at the local model from the previous tutorials, and give it real jobs — files, terminal, web — with an agent loop you can watch and control.