Accelerate Edge AI Development with Foundry Local
Microsoft announces Foundry Local 1.2.0 at Build 2026, expanding on-device edge AI development across platforms.
“These updates expand platform support, improve control over inference and acceleration, add new on-device APIs, and simplify deployment across disconnected, regulated, and sovereign environments.”
Microsoft announced Foundry Local 1.2.0 at Build 2026, adding multilingual real-time transcription, broader Linux and platform support, new on-device APIs, and Windows ML 2.0 acceleration for running AI locally without cloud dependency. It matters because it lowers the barrier to shipping production edge AI in privacy-sensitive, disconnected, and sovereign environments, advancing the industry shift toward local inference.