DLA-102-X: Optimized for Qualcomm Devices

dla is a machine learning model that can classify images from the Imagenet dataset. It is a architecture which can be used as backbone.

This is based on the implementation of DLA-102-X found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Getting Started

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime	Precision	Chipset	SDK Versions	Download
ONNX	float	Universal	QAIRT 2.37, ONNX Runtime 1.23.0	Download
ONNX	w8a8	Universal	QAIRT 2.37, ONNX Runtime 1.23.0	Download
QNN_DLC	float	Universal	QAIRT 2.42	Download
QNN_DLC	w8a8	Universal	QAIRT 2.42	Download
TFLITE	float	Universal	QAIRT 2.42, TFLite 2.17.0	Download
TFLITE	w8a8	Universal	QAIRT 2.42, TFLite 2.17.0	Download

For more device-specific assets and performance metrics, visit DLA-102-X on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

• Custom weights (e.g., fine-tuned checkpoints)
• Custom input shapes
• Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for DLA-102-X on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

• Model checkpoint: Imagenet
• Input resolution: 224x224
• Number of parameters: 26.3M
• Model size (float): 100 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
DLA-102-X	ONNX	float	Snapdragon® X Elite	2.927 ms	54 - 54 MB	NPU
DLA-102-X	ONNX	float	Snapdragon® 8 Gen 3 Mobile	2.074 ms	0 - 204 MB	NPU
DLA-102-X	ONNX	float	Qualcomm® QCS8550 (Proxy)	2.936 ms	0 - 293 MB	NPU
DLA-102-X	ONNX	float	Qualcomm® QCS9075	4.222 ms	0 - 4 MB	NPU
DLA-102-X	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.76 ms	0 - 156 MB	NPU
DLA-102-X	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	1.404 ms	0 - 161 MB	NPU
DLA-102-X	ONNX	w8a8	Snapdragon® X Elite	1.637 ms	28 - 28 MB	NPU
DLA-102-X	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	1.222 ms	0 - 213 MB	NPU
DLA-102-X	ONNX	w8a8	Qualcomm® QCS6490	72.856 ms	16 - 33 MB	CPU
DLA-102-X	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	1.698 ms	0 - 227 MB	NPU
DLA-102-X	ONNX	w8a8	Qualcomm® QCS9075	1.901 ms	0 - 3 MB	NPU
DLA-102-X	ONNX	w8a8	Qualcomm® QCM6690	40.155 ms	16 - 27 MB	CPU
DLA-102-X	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	1.117 ms	0 - 177 MB	NPU
DLA-102-X	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	38.02 ms	16 - 28 MB	CPU
DLA-102-X	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.908 ms	0 - 178 MB	NPU
DLA-102-X	QNN_DLC	float	Snapdragon® X Elite	3.154 ms	1 - 1 MB	NPU
DLA-102-X	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.002 ms	0 - 149 MB	NPU
DLA-102-X	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	14.466 ms	1 - 102 MB	NPU
DLA-102-X	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	2.891 ms	1 - 2 MB	NPU
DLA-102-X	QNN_DLC	float	Qualcomm® QCS9075	4.204 ms	1 - 3 MB	NPU
DLA-102-X	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	4.491 ms	0 - 124 MB	NPU
DLA-102-X	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.63 ms	0 - 104 MB	NPU
DLA-102-X	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.23 ms	1 - 106 MB	NPU
DLA-102-X	QNN_DLC	w8a8	Snapdragon® X Elite	1.582 ms	0 - 0 MB	NPU
DLA-102-X	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.958 ms	0 - 131 MB	NPU
DLA-102-X	QNN_DLC	w8a8	Qualcomm® QCS6490	3.913 ms	0 - 2 MB	NPU
DLA-102-X	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	3.221 ms	0 - 103 MB	NPU
DLA-102-X	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	1.388 ms	0 - 2 MB	NPU
DLA-102-X	QNN_DLC	w8a8	Qualcomm® QCS9075	1.578 ms	0 - 2 MB	NPU
DLA-102-X	QNN_DLC	w8a8	Qualcomm® QCM6690	10.73 ms	0 - 224 MB	NPU
DLA-102-X	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	1.869 ms	0 - 132 MB	NPU
DLA-102-X	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.791 ms	0 - 105 MB	NPU
DLA-102-X	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	1.698 ms	0 - 101 MB	NPU
DLA-102-X	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.618 ms	0 - 107 MB	NPU
DLA-102-X	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.017 ms	0 - 220 MB	NPU
DLA-102-X	TFLITE	float	Qualcomm® QCS8275 (Proxy)	14.461 ms	0 - 168 MB	NPU
DLA-102-X	TFLITE	float	Qualcomm® QCS8550 (Proxy)	2.747 ms	0 - 3 MB	NPU
DLA-102-X	TFLITE	float	Qualcomm® QCS9075	4.233 ms	0 - 57 MB	NPU
DLA-102-X	TFLITE	float	Qualcomm® QCS8450 (Proxy)	4.483 ms	0 - 181 MB	NPU
DLA-102-X	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.6 ms	0 - 169 MB	NPU
DLA-102-X	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.213 ms	0 - 168 MB	NPU
DLA-102-X	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.851 ms	0 - 138 MB	NPU
DLA-102-X	TFLITE	w8a8	Qualcomm® QCS6490	3.617 ms	0 - 29 MB	NPU
DLA-102-X	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	2.973 ms	0 - 102 MB	NPU
DLA-102-X	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	1.139 ms	0 - 3 MB	NPU
DLA-102-X	TFLITE	w8a8	Qualcomm® QCS9075	1.356 ms	0 - 29 MB	NPU
DLA-102-X	TFLITE	w8a8	Qualcomm® QCM6690	10.2 ms	0 - 207 MB	NPU
DLA-102-X	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	1.662 ms	0 - 138 MB	NPU
DLA-102-X	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.716 ms	0 - 106 MB	NPU
DLA-102-X	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	1.494 ms	0 - 89 MB	NPU
DLA-102-X	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.579 ms	0 - 106 MB	NPU

License

• The license for the original implementation of DLA-102-X can be found here.

References

• Deep Layer Aggregation
• Source Model Implementation

Community

• Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
• For questions or feedback please reach out to us.