In this blog, you'll learn best practices for running a self-hosted AI server with FileMaker 2025, including: Hardware and GPU recommendations. Key pitfalls to avoid when deploying production-ready large language models (LLMs). With Claris FileMaker 2025, you can now run your own AI Model Server using local infrastructure. Whether you're integrating text generation, text embedding, or image embedding models, self-hosting gives you full control over performance, cost, and data security—no cloud dependency required. Follow the steps for your path: bare metal (Ubuntu + Docker), VMware vSphere, or public cloud (Azure walkthrough below). Instead of depending on cloud APIs, you can bring the intelligence directly onto your own hardware, which unlocks: Improved privacy and security: With locally hosted AI, your data never. Building and setting up your very own high-performance local AI server offers a fantastic solution to this. Enabling you to tailor your server to your budget as well as keep all your responses, data and AI models secure and private using open source software. Network Engineer and tech enthusiast. Next, we'll deploy WebUI, so you can interact with your LLMs via a web browser. To do that, we're going to make use of WebUI. Here are the steps for installing Docker CE: Add the necessary GPG key with the following commands: You should see an empty. Yet, to implement AI models effectively, one needs powerful computing capacity, which is where an AI GPU server is needed.