Local AI › LM Studio

LM Studio: what it is, how to install it and requirements

Desktop app with a graphical interface to find, download and chat with models in GGUF or MLX format. It also has a local server.

Checked on 13 Oct 2026. Versions change every week: check the official site before installing.

How to install it

• Download the installer from lmstudio.ai/download, run it, open LM Studio, go to «Discover», search for a model, click «Download» and then «Chat». Official requirements: x64 CPU with AVX2 (or Arm64), 16 GB of RAM and at least 4 GB of dedicated VRAM recommended (system requirements).
• Download the .dmg from lmstudio.ai/download, drag it to Applications and follow the same steps. It needs macOS 14.0 or later on Apple Silicon, with 16 GB of RAM or more recommended (system requirements). On Apple Silicon you can pick models in MLX format.
• Download the AppImage (or the .deb) from lmstudio.ai/download, make it executable with chmod +x LM-Studio-*.AppImage and run it with ./LM-Studio-*.AppImage (the exact file name may vary). For servers there is llmster, a daemon with no graphical interface (same download page).

Install guides by system: Windows · Mac · Linux. Which model to download: Which local AI model to pick for your RAM: 8, 16, 24, 32 GB.

Other local AI tools

• Ollama: Engine and app to download and run language models with a single command. It includes a local API so other apps can connect to it.
• Jan: Open-source desktop app to chat with models offline, ChatGPT-style.
• GPT4All: Nomic's desktop app to chat locally and ask questions about your own documents (LocalDocs).
• llama.cpp: C/C++ library and command-line tools that many apps are built on and that define the GGUF format. The most technical option.
• Open WebUI: Self-hosted, ChatGPT-style web interface that connects to Ollama or OpenAI-compatible APIs.
• ComfyUI: Node-based interface to generate images and video with open models on your own computer.