Local AI Local AI Foundations

Install LM Studio

Download, install, and run your first local model with a GUI

49 of 66

What is LM Studio?

LM Studio is a desktop app for running local LLMs. It wraps download, chat, and server modes behind a clean interface. It is the fastest way to go from zero to a working local model.

Official site: lmstudio.ai

Install

  1. Download LM Studio from the official site: lmstudio.ai
  2. Open the installer
  3. Launch LM Studio

Available for macOS, Windows, and Linux.

Download your first model

Open the Search tab and pick a starter model:

  • Qwen 2.5 7B: fast, capable coding helper
  • Llama 3.1 8B: general purpose, well supported
  • DeepSeek-R1-Distill-Qwen 7B, reasoning model

Click Download. Models are stored under:

macOS:   ~/.cache/lm-studio/models/
Windows: %USERPROFILE%.cachelm-studiomodelsLinux:   ~/.cache/lm-studio/models/

Send your first prompt

  1. Go to the Chat tab
  2. Select your downloaded model from the dropdown
  3. Type: 
Write a Python function that reverses a string.

You should see a response generated entirely on your machine.

Verify it is local

Disconnect from the internet and send another prompt. If it still works, your model is truly local.

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