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 2.42, ONNX Runtime 1.24.3	Download
ONNX	w8a8	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a8	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.19.1	Download
TFLITE	w8a8	Universal	QAIRT 2.43, TFLite 2.19.1	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® 8 Elite Gen 5 Mobile	0.178 ms	0 - 23 MB	NPU
SqueezeNet-1.1	ONNX	float	Snapdragon® X2 Elite	0.19 ms	0 - 0 MB	NPU
SqueezeNet-1.1	ONNX	float	Snapdragon® X Elite	0.51 ms	2 - 2 MB	NPU
SqueezeNet-1.1	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.276 ms	0 - 30 MB	NPU
SqueezeNet-1.1	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.384 ms	1 - 58 MB	NPU
SqueezeNet-1.1	ONNX	float	Qualcomm® QCS9075	0.607 ms	1 - 3 MB	NPU
SqueezeNet-1.1	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.218 ms	0 - 24 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.213 ms	0 - 24 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® X2 Elite	0.219 ms	0 - 0 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® X Elite	0.485 ms	0 - 0 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.278 ms	0 - 31 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Qualcomm® QCS6490	3.659 ms	6 - 10 MB	CPU
SqueezeNet-1.1	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.38 ms	0 - 2 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Qualcomm® QCS9075	0.492 ms	0 - 3 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Qualcomm® QCM6690	2.992 ms	0 - 7 MB	CPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.23 ms	0 - 21 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	2.286 ms	0 - 7 MB	CPU
SqueezeNet-1.1	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.24 ms	1 - 25 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Snapdragon® X2 Elite	0.364 ms	1 - 1 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Snapdragon® X Elite	0.798 ms	1 - 1 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.455 ms	0 - 31 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	2.016 ms	0 - 22 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.656 ms	1 - 2 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® SA8775P	0.95 ms	1 - 22 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® QCS9075	0.867 ms	1 - 3 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	1.259 ms	0 - 32 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® SA7255P	2.016 ms	0 - 22 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® SA8295P	1.125 ms	0 - 18 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.33 ms	1 - 21 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.151 ms	0 - 22 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.249 ms	0 - 0 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® X Elite	0.493 ms	0 - 0 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.271 ms	0 - 29 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® QCS6490	1.023 ms	0 - 2 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	0.896 ms	0 - 21 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.369 ms	0 - 2 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® SA8775P	0.535 ms	0 - 22 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® QCS9075	0.447 ms	2 - 4 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® QCM6690	1.451 ms	0 - 19 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.434 ms	0 - 31 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® SA7255P	0.896 ms	0 - 21 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® SA8295P	0.713 ms	0 - 18 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.182 ms	0 - 23 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.372 ms	0 - 19 MB	NPU
SqueezeNet-1.1	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.242 ms	0 - 26 MB	NPU
SqueezeNet-1.1	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.449 ms	0 - 34 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® QCS8275 (Proxy)	2.035 ms	0 - 23 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® QCS8550 (Proxy)	0.663 ms	0 - 10 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® SA8775P	0.977 ms	0 - 24 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® QCS9075	0.875 ms	0 - 5 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® QCS8450 (Proxy)	1.277 ms	0 - 35 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® SA7255P	2.035 ms	0 - 23 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® SA8295P	1.153 ms	0 - 20 MB	NPU
SqueezeNet-1.1	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.332 ms	0 - 23 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.092 ms	0 - 22 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.14 ms	0 - 29 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® QCS6490	0.524 ms	0 - 3 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	0.61 ms	0 - 21 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.186 ms	0 - 1 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® SA8775P	0.375 ms	0 - 21 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® QCS9075	0.278 ms	0 - 3 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® QCM6690	0.93 ms	0 - 19 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.248 ms	0 - 30 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® SA7255P	0.61 ms	0 - 21 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® SA8295P	0.498 ms	0 - 17 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.102 ms	0 - 24 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