Chrome's 4GB AI model isn't new, but you're not wrong for being confused

Google has offered Gemini Nano for Chrome since 2024 as a lightweight, on-device model , but users reasonably expect the visible AI Mode to use the on-device model with queries staying local, when in fact every part of that inference is wrong—the AI Mode is cloud-backed and sends queries to Google's servers . Chrome holds the install state in Local State after the 4GB model is written to disk, and automatically re-downloads the model once the variations server tells Chrome the profile is eligible again .

Source: Ars Technica | 2026-05-08