LM Studio allows users to run and test open-source large language models (LLMs) on their local machines without needing an internet connection or cloud services, giving them full control over their data. However, integrating these models into external applications or production systems can be challenging due to the lack of a secure, authenticated API. Clarifai's Local Runners provide a solution by enabling users to serve AI models directly from their local hardware via a public API, without managing infrastructure or uploading data. This approach maintains data privacy and allows for seamless integration into existing workflows by routing API requests securely to the user’s machine, where computation occurs locally. The process involves using the Clarifai CLI to initialize and configure models from the LM Studio Model Catalog, customizing model scripts, and configuring settings through a YAML file. Once set up, users can start a Local Runner, receive a public URL, and run inference requests using OpenAI-compatible APIs or the Clarifai SDK, all while leveraging their local computational resources.