🎉 New: MCP support landed in LM Studio 0.3.17! Read the docs
LM StudioYour local AI toolkit.
Download and run Llama, DeepSeek, Qwen, Gemma on your computer.
By using LM Studio, you agree to its terms of use
Easy to start, much to explore
Discover and download open source models, use them in chats or run a local server
Easily run LLMs like Llama and DeepSeek on your computer. No expertise required
With LM Studio, you can ...
Cross-platform local AI SDK
LM Studio SDK: Build local AI apps without dealing with dependencies
pip install lmstudio
import lmstudio as lms llm = lms.llm() # Get any loaded LLM prediction = llm.respond_stream("What is a Capybara?") for token in prediction: print(token, end="", flush=True)
Frequently Asked Questions
TLDR: The app does not collect data or monitor your actions. Your data stays local on your machine.
No. One of the main reasons for using a local LLM is privacy, and LM Studio is designed for that. Your data remains private and local to your machine. Visit the Offline Operation page for more.
Yes! See our careers page for open positions.
LM Studio works on M1/M2/M3/M4 Macs, as well as Windows (x86 or ARM) and Linux PCs (x86) with a processor that supports AVX2. Visit the System Requirements page for the most up to date information.
You can run any compatible Large Language Model (LLM) from Hugging Face, both in GGUF (llama.cpp) format, as well as in the MLX format (Mac only). You can run GGUF text embedding models. Some models might not be supported, while others might be too large to run on your machine. Image generation models are not yet supported. See the Model Catalog for featured models.
The LM Studio GUI app is not open source. However LM Studio‘s CLI lms, Core SDK, and our MLX inferencing engine are all MIT licensed and open source. Moreover, LM Studio makes it easy to use leading open source libraries such as llama.cpp without needing the know-how to compile or integrate them yourself.
llama.cpp is a fantastic open source library that provides a powerful and efficient way to run LLMs on edge devices. It was created and is led by Georgi Gerganov. LM Studio leverages llama.cpp to run LLMs on Windows, Linux, and Macs.
MLX is a new Machine Learning framework from Apple. MLX is efficient and blazing fast on M1/M2/M3/M4 Macs. LM Studio leverages MLX to run LLMs on Apple silicon, utilizing the full power of the Mac's Unified Memory, CPU, and GPU. LM Studio's MLX engine (mlx-engine) is open source and available on GitHub (MIT). We would appreciate a star! We are also looking for community contributors.
Please fill out the LM Studio @ Work request form and we will get back to you as soon as we can.