
LM Studio is an innovative application that allows users to run local large language models (LLMs) entirely offline. With support for popular architectures such as Llama 3.2, Mistral, Phi, and more, it enables seamless interaction with your documents and models through an in-app chat interface or an OpenAI-compatible local server. Users can easily download compatible model files from Hugging Face and discover new LLMs right within the app. Its privacy-centric design ensures that your data remains local, making it ideal for personal and business use.

Experience the power of local LLMs without compromising your privacy.
LM Studio operates by utilizing advanced algorithms to run large language models locally on your device. It does this by leveraging the processing power of modern CPUs, particularly those that support AVX2, such as M1/M2/M3/M4 Macs and compatible Windows/Linux PCs. The application allows users to download compatible model files from Hugging Face repositories, enabling them to run various models without needing an internet connection. Once installed, users can engage with their local documents directly, chat through the in-app interface, or use a local server that mimics OpenAI's functionality. This means you can interact with your data securely without any external monitoring. The design focuses on user privacy, ensuring that all data processing occurs locally, thus maintaining confidentiality and security. Overall, LM Studio provides a streamlined experience for developers, researchers, and anyone interested in utilizing LLMs in a private and efficient manner.
To get started with LM Studio, simply download the application from our website. After installation, you can browse the Discover page to find compatible models to download. Once your models are downloaded, you can chat with your local documents through the in-app interface. For advanced users, you can also set up a local server compatible with OpenAI to run your models seamlessly alongside your projects. Enjoy a secure and private experience while exploring the vast capabilities of local LLMs!
Use LM Studio to chat with your documents locally, enhancing your research or study sessions.
Run tests on various LLMs for development purposes without compromising data privacy.
Conduct research in areas requiring LLM support without needing an internet connection.
Utilize local LLMs for business analytics while keeping sensitive data secure.
Experiment with different AI models and their capabilities without the need for internet access.
Ideal for learning about LLMs and experimenting with their functionalities.
No, LM Studio does not collect or monitor any user data. Your information stays local to your machine.
Yes, you can use LM Studio at work. Please fill out the LM Studio @ Work request form to get started.
You need an M1/M2/M3/M4 Mac, or a Windows/Linux PC with a processor that supports AVX2.
Yes, LM Studio is free for personal use.
LM Studio supports any GGUF Llama, Mistral, Phi, Gemma, StarCoder, and more.
You can find the technical documentation at the LM Studio documentation page.
You can download compatible model files directly from Hugging Face repositories within the app.
Yes, you can check our careers page for current job openings.
LM Studio is an innovative application that allows users to run local large language models (LLMs) entirely offline. With support for popular architectures such as Llama 3.2, Mistral, Phi, and more, it enables seamless interaction with your documents and models through an in-app chat interface or an OpenAI-compatible local server. Users can easily download compatible model files from Hugging Face and discover new LLMs right within the app. Its privacy-centric design ensures that your data remains local, making it ideal for personal and business use.
One app. Your entire coaching business
AI-powered website builder for everyone
AI dating photos that actually get matches
Popular AI tools directory for discovery and promotion
Product launch platform for founders with SEO backlinks
We tested the top AI blog writing tools to find the 5 best for SEO. Compare Jasper, Frase, Copy.ai, Surfer SEO, and Writesonic — with pricing, features, and honest pros/cons for each.
We tested 30+ AI coding tools to find the 12 best in 2026. Compare features, pricing, and real-world performance of Cursor, GitHub Copilot, Windsurf & more.