LM Studio
Provides a runtime to run large language models locally and privately on own hardware
It is a desktop application and runtime for running large language models locally on personal hardware, solving privacy, offline access, and cloud dependency issues associated with hosted AI. It sells to software developers and technical teams as well as individual consumers and businesses that want to use AI privately on their own machines. It is delivered as a free desktop app for Mac, Linux and Windows with a headless daemon, command-line tool, and SDKs that provide an OpenAI-compatible API for local and server deployment.
Key features
- Run LLMs locally on own hardware
- Private on-device inference
- Desktop app for Mac Linux Windows
- Headless daemon for servers
- Command-line tool (lms)
- JavaScript SDK
- Python SDK
- OpenAI-compatible API
- Apple MLX model support
- MCP client support
- Model hub exploration
- X0.5/day
- Blog
- Newsletter
- Community
- API
- Docs
- Changelog
- Software developers
- Consumers general
- Enterprises
Recent go-to-market activity
- 🔜 Coming to LM Studio Bionic.
X · lmstudio ·
A sample of the latest public posts. The full timeline, every channel and change alerts are available with a free account. See the full timeline →