Google I/O 印度大会圆满落幕!在与 Google Pixel 团队联合举办的特别展示中,我们正式揭晓了 Google Tensor 定制系统级芯片(SoC)和先进张量处理单元(TPU)如何驱动下一代强大、100% 私密的端侧 AI,该技术将应用于 Google Pixel 10 系列设备¹。
以下是 Google 印度 I/O 大会突破性展示的摘要:
推出适用于 TPU 的 Gemma 4 E2B
我们首次展示了适用于 TPU 的 Gemma 4 E2B——这是一款先进、强大且极其轻量的模型,专为在 Pixel TPU 上原生运行而设计。Gemma 4 确保你的数据永远不会离开设备,为边缘 AI 应用提供绝对的离线隐私保障。
智能体技能与移动端操作
我们演示了端侧 TPU 如何完全离线地充当个人旅行规划师、食谱指南或家庭自动化管家。此外,通过原生运行在 TPU 上的 FunctionGemma,用户可以使用仅限私密的语音或文本执行移动端操作,从而控制核心手机功能,如 WiFi 或地图。
智能体技能
移动端操作
丰富的离线多模态交互
我们展示了无需联网即可在文本、图像和音频之间无缝推理的能力:
AI 聊天:即时、深入的离线对话(即使在 30,000 英尺高空也能使用)。
图像问答:拍照并识别物体、植物或问题,无需任何网络连接。
音频问答:100% 私密的端侧音频转录,适用于讲座和笔记。
AI 聊天
图像问答
音频转录
真实世界的边缘应用
我们重点介绍了这项技术如何即刻改变各行各业:
零售:将食谱创意转化为精确、本地化的店内购物地图,完全离线完成。
汽车:让维修技师能够通过故障部件的照片进行现场视觉诊断。
零售应用场景
汽车应用场景
使用 Tensor SDK 进行开发
That's a wrap on Google I/O India! In a special joint showcase with the Google Pixel team, we officially unveiled how Google Tensor’s custom System-on-Chip (SoC) and advanced Tensor Processing Unit (TPU) are driving the next generation of powerful, 100% private on-device AI for from Google Pixel 10 family of devices1
Here is a summary of the groundbreaking Google India I/O Showcases:
Introducing Gemma 4 E2B for TPU
We debuted Gemma 4 E2B for TPU—a state-of-the-art, powerful, yet remarkably lightweight model designed to run natively on the Pixel TPU. Gemma 4 ensures your data never leaves the device, guaranteeing absolute offline privacy for edge AI applications.
Agent Skills & Mobile Actions
We demonstrated how your on-device TPU can act as a personal travel planner, recipe guide, or home automator completely offline. Additionally, using FunctionGemma running natively on the TPU, users can execute Mobile Actions to command core phone functions—like WiFi or maps—using just private voice or text.
Agent Skills
Mobile Action
Rich Offline Multimodal Interactions
We showcased seamless, internet-free reasoning across text, images, and audio:
AI Chat: Instant, deep offline conversations (even at 30,000 feet).
Ask Image: Snap and identify objects, plants, or issues with 0% internet.
Ask Audio: 100% private, on-device audio transcription for lectures and notes.
AI Chat
Ask Image
Ask Scribe
Real-World Edge Applications
We highlighted how this technology transforms industries right now:
Retail: Converting recipe ideas into precise, localized in-store shopping maps completely offline.
Automobile: Giving mechanics on-the-spot visual diagnostics from photos of faulty parts.
Retail Usecase
Automobile Usecase