Google launched Gemini Nano, the most optimized version of its new Gemini AI family, directly on the Pixel 8 Pro smartphone. Gemini Nano represents Google’s first on-device AI model, allowing the phone to handle advanced capabilities like summaries , language understanding and more without an Internet connection.
Specifically, Gemini Nano powers two notable new Pixel 8 features: “Summarize” in the Recorder transcription tool and suggested responses in Gboard. By keeping AI computing restricted to the device, Google can enable these features to work offline while ensuring better latency and reliability than solutions that rely on the cloud.
Gemini Nano is specially designed by Google to run efficiently on mobile chipsets compared to larger AI models. It uses the Tensor Processing Unit (TPU) in Google’s Tensor G3 mobile processor included in the Pixel 8. In addition, Gemini Nano will also be compatible with AI accelerators from major mobile silicon vendors such as Qualcomm, Samsung and MediaTek.
With Gemini Nano demonstrating the possibilities of powerful AI in smartphones, Google is poised to unlock more advanced capabilities by leveraging future iterations of its efficient models. Areas like Google Assistant, image processing, predictive typing, audio transcription, and more could be improved right on users’ phones for speed, privacy, and reliability. As software takes more advantage of on-device AI, Pixel phones will lead the way.
Categories: Technology
Source: vtt.edu.vn