Home
Chrome and Edge quietly raise local AI model storage needs to 20GB as browsers evolve into AI inference engines

Google Chrome and Microsoft Edge have raised the disk space requirements for local AI models to 20GB. These browsers silently download the models in the background to enable on-device AI capabilities. In May, Chrome was discovered to automatically download approximately 4GB of AI models to run features locally rather than sending all data to Google’s servers. Google has since quietly updated its official help documentation, increasing the required free disk space from 4GB to roughly 20GB. While this figure represents the download prerequisite, actual model usage may be lower.
Edge’s requirements largely mirror Chrome’s, also demanding 20GB of available space, but with an additional GPU memory threshold of at least 5.5GB. Microsoft noted that if available storage drops below 10GB, the models will be automatically deleted to ensure other browser functions operate smoothly. Fortunately, both browsers offer an option to disable the feature: Chrome allows users to turn off on-device AI in System settings, while Edge automatically cleans up models when storage is low. For users with ample storage, the impact is minimal, but it is worth noting that browsers consume significant storage space, particularly on devices with limited hard drive capacity.
Browsers Evolve into AI Runtime Environments
The sharp increase in local AI model demands reflects a fundamental shift in the role of browsers. Evolving from simple web rendering tools to extended ecosystem platforms, and now to on-device AI inference engines, 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, enhanced user privacy, and decreased reliance on cloud computing power, explaining why both Chrome and Edge are investing heavily in local AI.
However, the jump from 4GB to 20GB highlights that local AI model sizes are 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 5.5GB GPU memory requirement 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.
Related article
DeepSeek Unveils V4 Preview, Making 1M Long Context Accessible to All
DeepSeek has officially launched and open-sourced the preview version of its latest model series, DeepSeek-V4. Through structural innovations, this series achieves standardized ultra-long context handling of 1M (one million tokens) and leads domestic
Zhipu AI Targets $1 Billion ARR With Coding Focus After 5-Month 15x Growth
Multiple independent sources confirm that Zhipu’s Annual Recurring Revenue (ARR) hit $1 billion by July 2026. The company has not yet commented on these reports.AI coding and video generation have emerged as the fastest-growing commercial sectors for
Microsoft Unveils First Cybersecurity AI Model MAI-Cyber-1-Flash, Launches Perception Security Platform
Microsoft has officially introduced MAI-Cyber-1-Flash, its inaugural specialized cybersecurity model, alongside a new AI-driven security platform named Perception. Unveiled at a San Francisco event, these innovations reinforce Microsoft’s standing in
Related Special Topic Recommendations
Comments (0)
0/500

Google Chrome and Microsoft Edge have raised the disk space requirements for local AI models to 20GB. These browsers silently download the models in the background to enable on-device AI capabilities. In May, Chrome was discovered to automatically download approximately 4GB of AI models to run features locally rather than sending all data to Google’s servers. Google has since quietly updated its official help documentation, increasing the required free disk space from 4GB to roughly 20GB. While this figure represents the download prerequisite, actual model usage may be lower.
Edge’s requirements largely mirror Chrome’s, also demanding 20GB of available space, but with an additional GPU memory threshold of at least 5.5GB. Microsoft noted that if available storage drops below 10GB, the models will be automatically deleted to ensure other browser functions operate smoothly. Fortunately, both browsers offer an option to disable the feature: Chrome allows users to turn off on-device AI in System settings, while Edge automatically cleans up models when storage is low. For users with ample storage, the impact is minimal, but it is worth noting that browsers consume significant storage space, particularly on devices with limited hard drive capacity.
Browsers Evolve into AI Runtime Environments
The sharp increase in local AI model demands reflects a fundamental shift in the role of browsers. Evolving from simple web rendering tools to extended ecosystem platforms, and now to on-device AI inference engines, 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, enhanced user privacy, and decreased reliance on cloud computing power, explaining why both Chrome and Edge are investing heavily in local AI.
However, the jump from 4GB to 20GB highlights that local AI model sizes are 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 5.5GB GPU memory requirement 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.
DeepSeek Unveils V4 Preview, Making 1M Long Context Accessible to All
DeepSeek has officially launched and open-sourced the preview version of its latest model series, DeepSeek-V4. Through structural innovations, this series achieves standardized ultra-long context handling of 1M (one million tokens) and leads domestic
Zhipu AI Targets $1 Billion ARR With Coding Focus After 5-Month 15x Growth
Multiple independent sources confirm that Zhipu’s Annual Recurring Revenue (ARR) hit $1 billion by July 2026. The company has not yet commented on these reports.AI coding and video generation have emerged as the fastest-growing commercial sectors for
Microsoft Unveils First Cybersecurity AI Model MAI-Cyber-1-Flash, Launches Perception Security Platform
Microsoft has officially introduced MAI-Cyber-1-Flash, its inaugural specialized cybersecurity model, alongside a new AI-driven security platform named Perception. Unveiled at a San Francisco event, these innovations reinforce Microsoft’s standing in











