Google Chrome and Microsoft Edge have increased the disk space requirements for local AI models to 20GB. The browsers silently download these models in the background to support on-device AI features. In May of this year, Chrome was found to automatically download about 4GB of AI models to run AI features locally instead of uploading all data to Google's servers. Now, Google has quietly updated its official help documentation, raising the required free disk space from 4GB to about 20GB. This number is a prerequisite for downloading, but the actual model usage may be lower than this value.

Edge's requirements are largely consistent with Chrome, also requiring 20GB of available space, but with an additional GPU memory threshold: at least 5.5GB of video memory. Microsoft also stated that if available storage drops below 10GB, the models will be automatically deleted to ensure other browser functions run smoothly. Fortunately, both provide an option to turn off the feature—Chrome allows users to disable on-device AI features in the System settings, while Edge will automatically clean up models when storage is low. For users with ample storage, the impact is minimal, but it's worth noting that browsers secretly consume a significant amount of storage space, especially on devices with limited hard drive capacity.

Browsers Evolve into AI Runtime Environments

The sharp increase in demand for local AI models reflects a fundamental shift in the role of browsers. From a simple web rendering tool, to an extended ecosystem platform, and now to an on-device AI inference engine, browsers are taking on more computing tasks previously handled by operating systems or standalone applications. Running AI models locally offers core advantages such as reduced latency, protection of user privacy, and reduced reliance on cloud computing power, which explains why both Chrome and Edge are investing heavily in local AI.

However, the jump from 4GB to 20GB highlights that the size of local AI models is growing much faster than hardware storage improvements. For users with 256GB or smaller SSDs on lightweight laptops, 20GB of storage is no longer negligible, especially when multiple storage-heavy applications are installed simultaneously, increasing storage pressure. The additional requirement of 5.5GB of GPU memory for Edge further excludes many entry-level devices, meaning that the experience of local AI features will increasingly depend on hardware specifications. Browser developers need to find a more refined balance between AI feature richness and resource consumption, otherwise users may frequently choose to disable these features.