TensorFlow Lite is for mobile and embedded devices.

TensorFlow Lite is the official solution for running machine learning models on mobile and embedded devices. It enables on‑device machine learning inference with low latency and a small binary size on Android, iOS, and other operating systems.

Many benefits

On-device ML inference is difficult because of the many constraints—TensorFlow Lite can solve these:

  • lens


    TF Lite is fast with no noticeable accuracy loss—see the metrics.

  • lens


    Android, iOS, and more specialized IoT devices.

  • lens

    Low latency

    Optimized float- and fixed-point CPU kernels, op‑fusing, and more.

  • lens


    Integration with GPU and internal/external accelerators.

  • lens

    Small model size

    Controlled dependencies, quantization, and op registration.

  • lens


    Conversion, compression, benchmarking, power-consumption, and more.

Companies using TensorFlow Lite

“TensorFlow Lite helped us introduce machine learning and AI into our app in an easy and streamlined way. We could reduce the size of our models while keeping the accuracy high. This helped us create an amazing fishing experience for our users by allowing them to identify any fish species with just a photo.”

How it works



Build a new model or retrain an existing one, such as using transfer learning.


Convert a TensorFlow model into a compressed flat buffer with the TensorFlow Lite Converter.


Take the compressed .tflite file and load it into a mobile or embedded device.
See the tutorials below to build an app.

Build your first TensorFlow Lite app

Share your TensorFlow Lite story

We love to hear what you're working on—it may even get highlighted on our social media! Tell us.

“The release of TensorFlow Lite has allowed us to deploy an engaging real-time experience to our users that eliminates the requirement for a data connection. TensorFlow Lite’s ability to compress and optimize the TensorFlow graph for mobile deployment has been transformative in expanding the capabilities of Snap It.

Through TensorFlow Lite, our users can now enjoy a state of the art, computer-vision-based food logging experience without worrying about signal strength. We look forward to future collaborations with the TensorFlow Lite team.”