LM Studio is a free desktop application for macOS, Windows, and Linux that lets users discover, download, and run open-source large language models entirely on their own hardware without cloud connectivity. It provides a GUI for model management and chat, a local server that exposes an OpenAI-compatible API endpoint, and RAG support for chatting with local documents. It is widely used by developers and privacy-conscious users who want offline LLM inference. Key features: - GUI-based model discovery and download from Hugging Face (LLaMA, Mistral, DeepSeek, Qwen, Phi, and more) - Local OpenAI-compatible API server for drop-in integration with existing tools - Document chat with retrieval-augmented generation (RAG) on local files - Python and TypeScript SDKs for custom workflow integration - Cross-platform: macOS, Windows, Linux - Enterprise license with centralized model management and compliance controls
Free for personal and commercial team use. Enterprise license available (pricing not publicly listed). Commercial team licensing starts at $10/user/month according to third-party sources.