SqueezeNet-1.1: Optimized for Qualcomm Devices

SqueezeNet is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.

This is based on the implementation of SqueezeNet-1.1 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 2.45, ONNX Runtime 1.27.1	Download
ONNX	w8a8	Universal	QAIRT 2.45, ONNX Runtime 1.27.1	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
QNN_DLC	w8a8	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download
TFLITE	w8a8	Universal	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit SqueezeNet-1.1 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 SqueezeNet-1.1 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: 1.24M
Model size (float): 4.73 MB
Model size (w8a8): 1.30 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
SqueezeNet-1.1	ONNX	float	Snapdragon® X2 Elite	0.19 ms	2 - 2 MB	NPU
SqueezeNet-1.1	ONNX	float	Snapdragon® X Elite	0.372 ms	0 - 0 MB	NPU
SqueezeNet-1.1	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.267 ms	0 - 32 MB	NPU
SqueezeNet-1.1	ONNX	float	Snapdragon® 8 Gen 1 Mobile	0.566 ms	1 - 38 MB	NPU
SqueezeNet-1.1	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.385 ms	0 - 24 MB	NPU
SqueezeNet-1.1	ONNX	float	Qualcomm® QCS8450	0.566 ms	1 - 38 MB	NPU
SqueezeNet-1.1	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	0.606 ms	1 - 3 MB	NPU
SqueezeNet-1.1	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	0.372 ms	0 - 0 MB	NPU
SqueezeNet-1.1	ONNX	float	Qualcomm® Dragonwing™ Q-8750	0.221 ms	0 - 25 MB	NPU
SqueezeNet-1.1	ONNX	float	Snapdragon® 8 Elite Mobile	0.221 ms	0 - 25 MB	NPU
SqueezeNet-1.1	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.191 ms	0 - 20 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® X2 Elite	0.202 ms	1 - 1 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® X Elite	0.374 ms	0 - 0 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.273 ms	0 - 34 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® 8 Gen 1 Mobile	0.443 ms	0 - 37 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Qualcomm® Dragonwing™ QCS6490	0.962 ms	0 - 3 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.377 ms	0 - 4 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Qualcomm® QCS8450	0.443 ms	0 - 37 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Qualcomm® Dragonwing™ IQ-9075	0.501 ms	0 - 3 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Qualcomm® Dragonwing™ IQ-X7181	0.374 ms	0 - 0 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Qualcomm® Dragonwing™ Q-8750	0.235 ms	0 - 22 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® 8 Elite Mobile	0.235 ms	0 - 22 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.219 ms	0 - 23 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Snapdragon® X2 Elite	0.35 ms	1 - 1 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Snapdragon® X Elite	0.799 ms	1 - 1 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.45 ms	0 - 31 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	1.288 ms	0 - 37 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8275	2.133 ms	1 - 22 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.651 ms	1 - 2 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® SA8775P	0.932 ms	1 - 23 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® SA8650P	0.932 ms	1 - 23 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® SA8255P	0.932 ms	1 - 23 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® QCS8450	1.288 ms	0 - 37 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	0.986 ms	3 - 5 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	0.799 ms	1 - 1 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	0.328 ms	0 - 20 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® SA7255P	2.133 ms	1 - 22 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® SA8295P	1.144 ms	0 - 19 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Snapdragon® 8 Elite Mobile	0.328 ms	0 - 20 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.242 ms	1 - 22 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.242 ms	0 - 0 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® X Elite	0.471 ms	0 - 0 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.269 ms	0 - 28 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® 8 Gen 1 Mobile	0.43 ms	0 - 35 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® Dragonwing™ QCS6490	1.073 ms	0 - 2 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® Dragonwing™ QCS8275	0.946 ms	0 - 22 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.376 ms	0 - 17 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® SA8775P	0.545 ms	0 - 22 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® SA8650P	0.545 ms	0 - 22 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® SA8255P	0.545 ms	0 - 22 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® QCS8450	0.43 ms	0 - 35 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-9075	0.444 ms	0 - 2 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-X7181	0.471 ms	0 - 0 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-6690	1.434 ms	0 - 20 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-7790	0.371 ms	0 - 20 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-8750	0.181 ms	0 - 19 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® SA7255P	0.946 ms	0 - 22 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® SA8295P	0.718 ms	0 - 18 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® 8 Elite Mobile	0.181 ms	0 - 19 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.156 ms	0 - 20 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.371 ms	0 - 20 MB	NPU
SqueezeNet-1.1	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.45 ms	0 - 34 MB	NPU
SqueezeNet-1.1	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	1.272 ms	0 - 39 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® Dragonwing™ QCS8275	2.093 ms	0 - 24 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.651 ms	0 - 2 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® SA8775P	0.952 ms	0 - 26 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® SA8650P	0.952 ms	0 - 26 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® SA8255P	0.952 ms	0 - 26 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® QCS8450	1.272 ms	0 - 39 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	0.834 ms	0 - 5 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	0.336 ms	0 - 28 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® SA7255P	2.093 ms	0 - 24 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® SA8295P	1.139 ms	0 - 21 MB	NPU
SqueezeNet-1.1	TFLITE	float	Snapdragon® 8 Elite Mobile	0.336 ms	0 - 28 MB	NPU
SqueezeNet-1.1	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.248 ms	0 - 24 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.15 ms	0 - 29 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Snapdragon® 8 Gen 1 Mobile	0.25 ms	0 - 34 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® Dragonwing™ QCS6490	0.556 ms	0 - 3 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® Dragonwing™ QCS8275	0.625 ms	0 - 21 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.196 ms	0 - 2 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® SA8775P	0.375 ms	0 - 22 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® SA8650P	0.375 ms	0 - 22 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® SA8255P	0.375 ms	0 - 22 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® QCS8450	0.25 ms	0 - 34 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® Dragonwing™ IQ-9075	0.26 ms	0 - 3 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-6690	0.932 ms	0 - 19 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-7790	0.202 ms	0 - 19 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-8750	0.113 ms	0 - 19 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® SA7255P	0.625 ms	0 - 21 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® SA8295P	0.514 ms	0 - 18 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Snapdragon® 8 Elite Mobile	0.113 ms	0 - 19 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.1 ms	0 - 21 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.202 ms	0 - 19 MB	NPU

License

The license for the original implementation of SqueezeNet-1.1 can be found here.

References

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.

Downloads last month: -; Downloads are not tracked for this model. How to track

Paper for qualcomm/SqueezeNet-1.1

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

Paper • 1602.07360 • Published Feb 24, 2016 • 1