Page-1

# Architecture Source: [https://docs.qualcomm.com/doc/80-70014-54/topic/arch.html](https://docs.qualcomm.com/doc/80-70014-54/topic/arch.html) The TensorFlow Lite framework runs models on devices with low-power requirements, such as mobile, embedded, and edge platforms by optimizing them for latency, model size, and power consumption. The framework runs models with the help of delegates. Delegates are software layers that use libraries written to execute a neural network model efficiently on a specific hardware. Figure : TensorFlow Lite Runtime architecture - **[TensorFlow Lite Runtime](https://docs.qualcomm.com/doc/80-70014-54/topic/tensorflow-lite-runtime.html)** The TensorFlow Lite on-device inference loads the model into an interpreter, which parses the model and uses a delegate to run it. - **[Delegates](https://docs.qualcomm.com/doc/80-70014-54/topic/delegates.html)** Delegates help you offload the TensorFlow Lite graph execution to the CPU, GPU, and Hexagon Tensor Processor hardware accelerators. Last Published: Jul 12, 2024 [Previous Topic Run a TensorFlow Lite model using a native TensorFlow Lite sample application](https://docs.qualcomm.com/bundle/publicresource/80-70014-54/topics/run-a-tensorflow-lite-model-using-a-native-tensorflow-lite-sample-application.md) [Next Topic TensorFlow Lite Runtime](https://docs.qualcomm.com/bundle/publicresource/80-70014-54/topics/tensorflow-lite-runtime.md)