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 2.37, 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 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® X Elite	0.489 ms	2 - 2 MB	NPU
SqueezeNet-1.1	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.431 ms	0 - 100 MB	NPU
SqueezeNet-1.1	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.601 ms	0 - 50 MB	NPU
SqueezeNet-1.1	ONNX	float	Qualcomm® QCS9075	0.882 ms	1 - 3 MB	NPU
SqueezeNet-1.1	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.327 ms	0 - 87 MB	NPU
SqueezeNet-1.1	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.274 ms	0 - 91 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® X Elite	0.496 ms	0 - 0 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.454 ms	0 - 99 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Qualcomm® QCS6490	3.777 ms	5 - 9 MB	CPU
SqueezeNet-1.1	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.563 ms	0 - 40 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Qualcomm® QCS9075	0.682 ms	0 - 3 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Qualcomm® QCM6690	2.928 ms	0 - 7 MB	CPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.336 ms	0 - 93 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	2.13 ms	0 - 7 MB	CPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.302 ms	0 - 93 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Snapdragon® X Elite	0.783 ms	1 - 1 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.446 ms	0 - 31 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	0.952 ms	0 - 22 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® QCS9075	0.864 ms	1 - 3 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	1.27 ms	0 - 32 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® SA8295P	1.145 ms	0 - 18 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.326 ms	0 - 24 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.239 ms	1 - 25 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® X Elite	0.49 ms	0 - 0 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.263 ms	0 - 30 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® QCS6490	1.076 ms	0 - 2 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	0.944 ms	0 - 21 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.379 ms	0 - 9 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® SA8775P	0.543 ms	0 - 21 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® QCS9075	0.443 ms	0 - 2 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® QCM6690	1.461 ms	0 - 19 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.438 ms	0 - 31 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® SA7255P	0.944 ms	0 - 21 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® SA8295P	0.717 ms	0 - 18 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.178 ms	0 - 23 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.382 ms	0 - 20 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.149 ms	0 - 22 MB	NPU
SqueezeNet-1.1	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.45 ms	0 - 34 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® QCS8275 (Proxy)	5.915 ms	0 - 27 MB	GPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® QCS8550 (Proxy)	0.67 ms	0 - 2 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® SA8775P	4.018 ms	0 - 25 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® QCS9075	0.878 ms	0 - 5 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® QCS8450 (Proxy)	1.273 ms	0 - 34 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® SA7255P	5.915 ms	0 - 27 MB	GPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® SA8295P	1.167 ms	0 - 20 MB	NPU
SqueezeNet-1.1	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.33 ms	0 - 27 MB	NPU
SqueezeNet-1.1	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.237 ms	0 - 27 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.15 ms	0 - 28 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® QCS6490	0.516 ms	0 - 3 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	0.63 ms	0 - 23 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.2 ms	0 - 1 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® SA8775P	0.374 ms	0 - 22 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® QCS9075	0.268 ms	0 - 3 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® QCM6690	0.919 ms	0 - 18 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.264 ms	0 - 29 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® SA7255P	0.63 ms	0 - 23 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® SA8295P	0.501 ms	0 - 17 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.105 ms	0 - 23 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.208 ms	0 - 19 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.097 ms	0 - 22 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