# Convert a TensorFlow or Keras model to TensorFlow Lite format

Source: [https://docs.qualcomm.com/doc/80-70014-54/topic/convert-a-tensorflow-or-keras-model-to-tensorflow-lite-format.html](https://docs.qualcomm.com/doc/80-70014-54/topic/convert-a-tensorflow-or-keras-model-to-tensorflow-lite-format.html)

The TensorFlow framework provides Python APIs and CLI tools to convert a TensorFlow
        or Keras model to the TensorFlow Lite format.

- Python APIs: TensorFlow offers APIs to convert, optimize, and quantize models to the
                TensorFlow Lite format.
- CLI: A CLI tool is available for converting models to the TensorFlow Lite format,
                but it is suitable for basic model conversion only.

Note: TensorFlow to TensorFlow Lite Python APIs offer more flexibility
            to convert, optimize, and quantize models to suit your requirements.

- **[Convert and quantize using Python APIs](https://docs.qualcomm.com/doc/80-70014-54/topic/convert-and-quantize-using-python-apis.html)**  

TensorFlow offers APIs to convert a TensorFlow Saved Model or a Keras model to a         TensorFlow Lite model.
- **[Convert using offline converter tool (CLI)](https://docs.qualcomm.com/doc/80-70014-54/topic/convert-using-offline-converter-tool-cli.html)**  

The TensorFlow Lite converter tool, tflite\_convert, which can be used offline, is         included in the TensorFlow pip package for TensorFlow versions 2.x and above.

**Parent Topic:** [Convert TensorFlow Lite models](https://docs.qualcomm.com/doc/80-70014-54/topic/convert-tensorflow-lite-models.html)

Last Published: Jul 12, 2024

[Previous Topic
Use an existing TensorFlow Lite model](https://docs.qualcomm.com/bundle/publicresource/80-70014-54/topics/use-an-existing-tensorflow-lite-model.md) [Next Topic
Convert and quantize using Python APIs](https://docs.qualcomm.com/bundle/publicresource/80-70014-54/topics/convert-and-quantize-using-python-apis.md)