Overview

TensorFlow Lite is an open source software library for running machine learning models on mobile and embedded devices. For more information, see www.tensorflow.org/lite.

For memory constrained devices, the library contains TensorFlow Lite for Microcontrollers. For more information, see www.tensorflow.org/lite/microcontrollers.

The MCUXpresso Software Development Kit (MCUXpresso SDK) provides a comprehensive software package with a pre-integrated TensorFlow Lite for Microcontrollers based on version 25-04-08 (from the 8th of April 2025 with commit ). This document describes the steps required to download and start using the library. Additionally, the document describes the steps required to create an application for running pre-trained models.

Note: The document also assumes knowledge of machine learning frameworks for model training.

TensorFlow Lite for Microcontrollers

TensorFlow Lite for Microcontrollers is a port of TensorFlow Lite designed to run machine learning models on DSPs, microcontrollers and other devices with limited memory.

Additional Links:

Build Status

Official Builds

Build Type

Status

CI (Linux)

CI

Code Sync

Sync from Upstream TF

Community Supported TFLM Examples

This table captures platforms that TFLM has been ported to. Please see New Platform Support for additional documentation.

Platform

Status

Arduino

Arduino Antmicro

Coral Dev Board Micro

TFLM + EdgeTPU Examples for Coral Dev Board Micro

Espressif Systems Dev Boards

ESP Dev Boards

Renesas Boards

TFLM Examples for Renesas Boards

Silicon Labs Dev Kits

TFLM Examples for Silicon Labs Dev Kits

Sparkfun Edge

Sparkfun Edge

Texas Instruments Dev Boards

Texas Instruments Dev Boards

Community Supported Kernels and Unit Tests

This is a list of targets that have optimized kernel implementations and/or run the TFLM unit tests using software emulation or instruction set simulators.

Build Type

Status

Cortex-M

Cortex-M

Hexagon

Hexagon

RISC-V

RISC-V

Xtensa

Xtensa

Generate Integration Test

Generate Integration Test

Contributing

See our contribution documentation.

Getting Help

A Github issue should be the primary method of getting in touch with the TensorFlow Lite Micro (TFLM) team.

The following resources may also be useful:

  1. SIG Micro email group and monthly meetings.

  2. SIG Micro gitter chat room.

  3. For questions that are not specific to TFLM, please consult the broader TensorFlow project, e.g.:

Additional Documentation

RFCs

  1. Pre-allocated tensors

  2. TensorFlow Lite for Microcontrollers Port of 16x8 Quantized Operators