LM Studio is a desktop app for running large language models (LLMs) locally on your own computer.

features
<ul><li>Run Local LLMs Offline — Execute open-weight models entirely on your own device without cloud
dependency.</li><li>Cross-Platform Support — Available on Windows, macOS, and Linux.</li><li>Model Discovery &amp; Download — Browse and download GGUF/MLX models directly from Hugging
Face.</li><li>Built-in Chat Interface — Interact with local models through a clean ChatGPT-like UI.</li><li>OpenAI-Compatible API Server — Serve local models via OpenAI-style REST endpoints for app
integration.</li><li>Document Chat (RAG) — Chat with local documents privately and offline.</li><li>Model Management — Organize models, prompts, presets, and configurations in one place.</li><li>Developer Tooling — Includes CLI, Python SDK, TypeScript SDK, and REST</li><li>Headless Mode — Run LM Studio without GUI for servers or CI environments.</li><li>MCP Integration — Connect MCP servers and external AI workflows.</li><li>Privacy-First Design — Prompts and conversations stay on the local machine.</li><li>Hardware-Aware Optimization — GPU offloading and memory controls for better performance on
limited hardware.</li><li>Multi-Model Support — Supports Llama, Qwen, Mistral, Gemma, Phi, DeepSeek, and more.</li><li>Local Network Serving — Expose local models across devices on the same network.</li></ul>