# Summary: Google AI Edge Gallery
Google has released an official application called AI Edge Gallery that enables users to run Gemma 4 language models directly on iPhones without requiring internet connectivity. The app supports multiple model sizes, including the E2B and E4B variants of Gemma 4, as well as select models from the Gemma 3 family. The E2B model requires a 2.54GB download and reportedly delivers both speed and capable performance.
The application represents Google's effort to bring on-device AI processing to consumers through a native iOS experience. By running models locally on the device rather than relying on cloud servers, users gain privacy benefits and reduced latency for AI tasks. The app reportedly functions effectively, suggesting that smaller language models can now deliver practical utility on consumer smartphones.
This development matters because it democratizes access to AI capabilities while addressing privacy concerns associated with cloud-based processing. As on-device AI becomes more viable, users gain greater control over their data while developers gain a platform to test local model deployment. The app's apparent success indicates that the threshold for practical on-device AI on consumer hardware has been reached, potentially shifting how companies approach AI feature integration.
Key Takeaways
- # Summary: Google AI Edge Gallery Google has released an official application called AI Edge Gallery that enables users to run Gemma 4 language models directly on iPhones without requiring internet connectivity.
- The app supports multiple model sizes, including the E2B and E4B variants of Gemma 4, as well as select models from the Gemma 3 family.
- 54GB download and reportedly delivers both speed and capable performance.
- The application represents Google's effort to bring on-device AI processing to consumers through a native iOS experience.
Read the full article on Simon Willison
Read on Simon Willison