Low latencyOptimized float- and fixed-point CPU kernels, op‑fusing, and more.
AccelerationIntegration with GPU and internal/external accelerators.
Pick a model
Pick a new model or retrain an existing one.
Convert a TensorFlow model into a compressed flat buffer with the TensorFlow Lite Converter.
Take the compressed
.tflitefile and load it into a mobile or embedded device.
[optional] Quantize by converting 32-bit floats to more efficient 8-bit integers or run on GPU.