LM Studio

LM Studio is a desktop application that enables users to run large language models (LLMs) directly on their own hardware, without any internet connection or cloud dependency. It supports a wide range of open-source models including gpt-oss, Qwen, Gemma, DeepSeek, and many others. Users can download these models and execute them locally on Windows, macOS, or Linux machines, ensuring complete data privacy and control. The software provides a graphical user interface for easy model loading, configuration, and interaction, making it accessible for both casual users and developers. Beyond the GUI version, LM Studio offers a headless deployment option called llmster, which strips away the graphical interface and allows the core engine to run on servers, cloud instances, or even within CI/CD pipelines. This headless mode is installed via simple command-line scripts (curl or PowerShell), enabling automated and scalable inference in production environments. For developers, LM Studio provides official SDKs for JavaScript (npm package) and Python (pip package), along with comprehensive API documentation. These SDKs allow integration of local LLM capabilities into custom applications, chatbots, or data processing pipelines, with full control over model parameters and inference settings. The application is free for both personal and work use, with no subscription or usage limits. It supports running models on GPU or CPU, and can leverage multiple GPUs for larger models. The local execution avoids any data being sent to external servers, making it suitable for handling sensitive information, proprietary data, or scenarios requiring strict compliance (e.g., healthcare, finance, legal). The built-in model manager allows users to browse, download, and update models from Hugging Face or