Featured on Locally Hosted: Run Full LLMs Locally with Microsoft Foundry Local 🎬

[ryanstorandt]

I recently hosted an episode of my Locally Hosted podcast where we dove deep into your work on Foundry Local. We really appreciated how you’ve simplified running full LLMs locally, and we highlighted its seamless support for chat-completions, GPU acceleration, and private AI workflows.

For production, we ran our entire pipeline locally on an NVIDIA DGX Spark. We generated the AI dialogue with Qwen 3.6, created the visuals using CogVideoX-2B, and synthesized the narration with Edge-TTS voices—all without leaving the machine.

We’re also working on open-sourcing our complete pipeline soon so the community can build on it. Thank you so much for your incredible contribution to the local AI ecosystem. It’s truly inspiring to see projects like yours empowering developers to run powerful models privately and efficiently. Looking forward to future updates!

🎬 Catch the episode here: https://youtu.be/EXLAV7vAFwI