Run AI Locally: Getting Started with Azure Foundry Local
Details
Agenda:
6:00 PM - 7:30 PM - Run AI Locally: Getting Started with Azure Foundry Local
Abstract:
What if you could run powerful AI models directly on your laptop — no cloud subscription, no data leaving your machine, no latency? In this session, we'll explore Azure Foundry Local, Microsoft's new tool that brings enterprise-grade AI inference to your local device.
We'll walk through installing Foundry Local on Windows and macOS, running your first model in under 5 minutes, and using the CLI to manage, switch, and cache models. We'll also cover hardware acceleration (NVIDIA, AMD, Intel NPU, Apple Silicon), explore the model catalog, and see how Foundry Local integrates with popular inference SDKs for building real applications.
Whether you're a developer who wants to prototype AI apps offline or a tech enthusiast curious about local AI, this session will get you up and running fast.
Takeaways:
- Install and run AI models locally with a single CLI command
- Understand hardware acceleration options and model variants
- Connect Foundry Local to your own apps via the OpenAI-compatible API
- Know when to run local vs. cloud AI
