# TFLite Model Conversion

Machine Learning frameworks have specific formats for storing
neural network models. Qualcomm® Neural Processing SDK supports these various models by
converting them to a framework neutral **deep learningcontainer (DLC)** format. The DLC file is used by the Qualcomm® Neural Processing SDK
runtime for execution of the neural network.

A trained Tensorflow model can be converted to a TFLte model
(.tflite) file using the instructions at
[https://www.tensorflow.org/lite/convert#python_api_](https://www.tensorflow.org/lite/convert#python_api_)

The
[snpe-tflite-to-dlc](https://docs.qualcomm.com/doc/80-63442-2/topic/tools.html#snpe-tflite-to-dlc)
tool converts a TFLite model into an equivalent Qualcomm® Neural Processing SDK DLC file.
The following command will convert an Inception v3 TFLite model
into a Qualcomm® Neural Processing SDK DLC file.

snpe-tflite-to-dlc --input_network inception_v3.tflite
                       --input_dim input "1,299,299,3"
                       --output_path inception_v3.dlc
    Copy to clipboard

The Inception v3 model files can be obtained from
[https://tfhub.dev/tensorflow/lite-model/inception_v3/1/default/1](https://tfhub.dev/tensorflow/lite-model/inception_v3/1/default/1)

Note:

- To check the list of currently supported TFlite Ops, see [Op
Support Table](https://docs.qualcomm.com/doc/80-63442-2/topic/network_layers.html#network_layers).
- Qualcomm® Neural Processing SDK and TFlite Converter currently only support float input
data types.
- There are some known issues with certain older versions of
MLIR based TFLite converter that can lead to failure loading
the model.

Last Published: Oct 02, 2025

[Previous Topic
Tensorflow Graph Compatibility](https://docs.qualcomm.com/bundle/publicresource/80-63442-2/topics/tensorflow_graphs.md) [Next Topic
PyTorch Model Conversion](https://docs.qualcomm.com/bundle/publicresource/80-63442-2/topics/model_conv_pytorch.md)