Brifing

Unlocking the Next Era of On-Device AI with Google Tensor and Pixel

Google Pixel 10 series shapes the future with powerful and fully private on-device AI.

Google Developers Blog1 min

1The Power of Google Tensor and TPU

Google Tensor SoC and advanced Tensor Processing Unit (TPU) deliver powerful and fully private on-device AI for the Pixel 10 series. This technology ensures data stays on the device, prioritizing privacy.

2Gemma 4 E2B Model

Gemma 4 E2B was introduced as a lightweight and powerful model running natively on the Pixel TPU. This model offers seamless and internet-free experiences for edge AI applications.

3Personal Assistant Features

The on-device TPU can function as a personal travel planner, recipe guide, or home automation tool entirely offline. It also allows users to control core phone functions via voice or text commands.

4Multimodal Interactions

Seamless and internet-free intelligent interactions across text, images, and audio are provided. This enables users to engage in deep conversations, identify objects, and take voice notes.

5Real-World Applications

This technology is revolutionizing industries like retail and automotive. For instance, it can convert recipes into shopping maps entirely offline or provide visual diagnostics for faulty parts.

6Tensor SDK for Developers

The Tensor SDK offers developers a unified workflow and over 100 classical ML models. It provides the necessary tools to build secure and edge-based AI applications.

Original article: Google Developers Blog — Google Tensor ve Pixel ile Cihaz Üzeri AI'nin Yeni Çağı