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:
-
Low latency
Optimized float- and fixed-point CPU kernels, op‑fusing, and more. -
Acceleration
Integration with GPU and internal/external accelerators.
-
Small model size
Controlled dependencies, quantization, and op registration. -
Tooling
Conversion, compression, benchmarking, power-consumption, and more.
How it works
Pick a model
Pick a new model or retrain an existing one.
Convert
Convert a TensorFlow model into a compressed flat buffer with the TensorFlow Lite Converter.
Deploy
Take the compressed
.tflite file and load it into a mobile or embedded device.
Optimize
[optional] Quantize by converting 32-bit floats to more efficient 8-bit integers or run on GPU.
Build your first TensorFlow Lite app with Codelabs
Get started
- Beginner: TensorFlow for Poets
- Beginner: TensorFlow for Poets 2: Android
- Beginner: TensorFlow for Poets 2: iOS
- Intermediate: Object detection tutorial
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.
TensorFlow Lite users
