LM Studio

LM Studio is a cross-platform desktop application for macOS, Windows, and Linux that enables users to run large language models (LLMs) entirely on their own hardware. It provides a user-friendly interface to browse and download thousands of models from Hugging Face, supporting GGUF and Apple’s MLX formats. Key features include a private chat interface, a local inference server with OpenAI-compatible API endpoints for developers, support for RAG (Retrieval Augmented Generation), and dedicated Python and JavaScript SDKs. The tool is designed for privacy-conscious users and developers who need high-performance local AI without cloud dependency.