You are using an out of date browser. It may not display this or other websites correctly. You should upgrade or use an alternative browser.
on-device llms
About this tag
On-device LLMs are small language models designed to run AI workloads locally on Windows 11 PCs, using CPUs, GPUs, and NPUs without relying on cloud servers. Microsoft's Aion 1.0 Instruct and Aion 1.0 Plan, announced at Build 2026, exemplify this approach, enabling tasks like instruction following and planning directly on the device. This shift aims to make Windows a platform for local AI infrastructure, enhancing privacy and reducing latency. Discussions on WindowsForum cover the implications for enterprise IT, security, and developer APIs, focusing on how on-device LLMs integrate with Windows 11 to support agent-era applications while keeping data processing on the PC.
Microsoft announced Aion 1.0 Instruct and Aion 1.0 Plan at Build 2026 on June 2, positioning the new on-device small language models as part of a broader Windows 11 push to run AI workloads locally across CPUs, GPUs, and NPUs. The announcement is not just another model drop in a season full of...