LM Studio

LM Studio is a desktop application for downloading, running, and serving local large language models (LLMs) on macOS, Windows, and Linux.

LM Studio provides a built-in model catalog and importer for popular local formats such as GGUF and MLX, along with an offline-first chat interface. The app also supports attaching files to chats to add context through retrieval-augmented generation, which makes it useful for local document Q&A without sending data to external services.

For developers, LM Studio can expose locally loaded models over an OpenAI-compatible API for chat completions and embeddings, and it offers official Python and TypeScript SDKs. It also offers an lms command-line tool for scripting tasks like loading models and starting the local server. The CLI and SDKs include controls for load-time configuration such as context length and GPU offload.

Official website: lmstudio.ai