LM Studio
LM Studio is a desktop application that allows you to discover, download, and run large language models (LLMs) locally on your computer. It provides a clean graphical interface for model management and chat, eliminating the need for cloud APIs or command-line tools.
Overview
LM Studio supports models in GGUF format and provides a local server compatible with the OpenAI API format, making it easy to integrate with existing applications. It uses llama.cpp under the hood for efficient CPU and GPU inference.
Key Features
- Model Discovery: Browse and download models from Hugging Face Hub directly from the app
- Local Inference: Run models entirely on your hardware — no cloud required
- OpenAI-Compatible Server: Local API endpoint that mimics the OpenAI Chat Completions API format
- Hardware Acceleration: Supports CUDA (NVIDIA), Metal (Apple Silicon), and Vulkan for GPU inference
- Chat Interface: Built-in chat UI for testing and interacting with models
- Multiple Model Formats: Supports GGUF and other llama.cpp-compatible formats
Licensing
LM Studio uses a freemium model:
- Free Tier: The core application is free for personal use, with model downloading and local inference
- Commercial: Commercial use requires a paid license. The app itself is free but certain features or redistribution may require licensing
See LM Studio Licensing for details.
Official Resources
- Website: https://lm.studio
- GitHub: https://github.com/lmstudio-ai