Google announced the Gemma 4 E2B model, optimized for use with the Pixel 10's Tensor Processing Unit. This update expands the device's capabilities for AI-driven tasks, emphasizing offline usage and multimodal interactions.
Google introduced the Gemma 4 E2B model designed to run on the Pixel 10's Tensor Processing Unit. This announcement was made during the I/O Connect India event. Gemma 4 was previously revealed in April as the foundation for the upcoming Gemini Nano 4 model.
The new model features advanced multimodal capabilities such as AI Chat for offline conversations, image recognition without internet access, and private audio transcription. These features enhance user interaction and productivity without relying on cloud connectivity.
Gemma 4 is designed for practical use cases, including creating in-store shopping maps from recipes and providing visual diagnostic assistance for mechanics through photos of car parts. This functionality demonstrates the model's effectiveness in various industry settings.
Gemma 4 is compatible with multiple Pixel 10 variants, including the Pixel 10, 10 Pro, 10 Pro XL, and 10 Pro Fold. This ensures broader access for users to leverage the model's capabilities directly on their devices.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
Google announced the Gemma 4 E2B model, optimized for use with the Pixel 10's Tensor Processing Unit. This update expands the device's capabilities for AI-driven tasks, emphasizing offline usage and multimodal interactions.