Sign up for experimental access to Google Tensor ML SDK

Google Tensor ML SDK empowers you to build on-device machine learning capabilities specifically for Google Pixel phones, while leveraging Google Pixel's custom-designed Tensor System-on-Chip (SoC) with its dedicated Tensor Processing Unit (TPU) inference accelerator.

---

Sign up for experimental access

Experimental access is for developers to try using Google Tensor ML SDK before general availability. By signing up for it, you agree to these terms that apply to your use of Google Tensor ML SDK.

---

Key features

• Access a curated collection of open-source, SDK-compatible models using Model Garden.
• Visualize model architecture for better understanding of on-device performance.
• Ensure TPU compatibility by checking operation support within your models.
• Analyze the estimated latency of individual operations on the TPU.
• Profile inference performance by comparing CPU and TPU execution on a Pixel device.

Note: There is no guarantee that a feature in experimental access will ever become generally available. It may remain an experimental access feature indefinitely, be shutdown, or be combined with other features into packages designed for specific developer audiences. Some experimental access features may eventually become generally available, but there is no fixed release schedule.