microsoft has updated the windows 11 local AI documentation to confirm that the language model APIs can now run on PCs that are not equipped with Co-pilot+ but they have compatible GPUs. Previously, these APIs were only available on Copilot+ PCs that had dedicated NPU hardware.
The change is currently targeted at developers and is not yet available to end users. Supported hardware includes Nvidia GeForce RTX 30 series GPUs and newer models with at least 6GB of VRAM.
What changed and what does this allow on PCs that are not Copilot+
Updated documentation for Microsoft developers and a GitHub The post describes a recent change. They claim that the language model APIs now run on GPU-equipped PCs that are not Copilot+ models, expanding the capabilities of the local language model to more Windows 11 devices.
This represents a change from Microsoft’s original approach in the Copilot+ PCs released on June 18, 2024, which emphasized that NPUs were necessary for local AI functions in Windows.
While NPUs are not the only chips capable of supporting AI workloads, Microsoft previously limited most integrated AI functions to devices with NPUs.
The current feature set focuses on text-based tasks that use the Windows.AI.Text APIs. These capabilities include summarizing content, rewriting text, converting text to structured formats, and generating prompts.
Although the functionality resembles cloud-based AI tools, it runs locally on the device, reducing reliance on cloud processing and keeping data on the machine.
Essentially, there is a small model on the device called Phi Silica. Instead of being preinstalled on all systems, Phi Silica can be downloaded through Windows Update whenever an application needs it. Once installed, the model runs locally and uses the GPU when available.
What’s still limited and why GPU support is important for Windows 11 users
Currently, GPU support is limited to the API layer of the language model. Other Copilot+ features remain tied to NPU-equipped systems, including:
- windows recovery,
- Click to Do and several other Copilot+ branded AI integrations.
This capability is primarily accessible at the developer level and not directly to end users. Running these APIs requires applications built or adapted to use the Windows AI framework. Users will see benefits as developers update their applications to support GPU-based local AI on non-Copilot+ PCs.
The update expands the range of Windows 11 devices that can run local AI features. Mid-to-high-end Nvidia GPU PCs that previously lacked NPU hardware now have a way to access Microsoft’s built-in local AI tools.
Many gaming computers and workstations meet this new GPU requirement, enabling local AI capabilities for a sizable portion of Windows 11 users.
Microsoft has not indicated whether GPU support will be expanded to Windows Recall and other features currently limited to Copilot+ hardware, or whether AMD and Intel GPUs will gain similar support in the future.
