> ## Documentation Index
> Fetch the complete documentation index at: https://dragonwingdocs.qualcomm.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Export an ONNX model to LiteRT

> Convert an ONNX model to LiteRT format for deployment on Qualcomm Dragonwing IoT platforms using the ONNX → TensorFlow → LiteRT conversion path.

You can convert ONNX models to LiteRT format and optimize them for on-device inference. Converting an ONNX model to LiteRT is a two-step process:

**ONNX → TensorFlow (SavedModel) → LiteRT**

## Convert an ONNX model to TensorFlow

Use the `onnx-tf` module to convert an ONNX model to a TensorFlow SavedModel. This is the commonly used and stable approach.

1. Install the required dependencies:

   ```shell theme={null}
   pip install onnx onnx-tf tensorflow
   ```

2. Convert the ONNX model to TensorFlow SavedModel format:

   ```shell theme={null}
   onnx_model_path=my_model.onnx
   tf_model_path=tf_model
   onnx-tf convert -i ${onnx_model_path} -o ${tf_model_path}
   ```

## Convert TensorFlow to LiteRT

Convert the TensorFlow SavedModel to LiteRT format:

```python theme={null}
import tensorflow as tf

converter = tf.lite.TFLiteConverter.from_saved_model("tf_model")
tflite_model = converter.convert()

with open("model.tflite", "wb") as f:
    f.write(tflite_model)
```

## Quantize the model

To quantize the converted LiteRT model for improved performance on the NPU, see [Quantize models using full integer quantization](../topic/export-tf-model-litert#full-integer-quantization).