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 1.24.1	Download
ONNX	w8a8	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a8	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.17.0	Download
TFLITE	w8a8	Universal	QAIRT 2.43, 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	0.492 ms	2 - 2 MB	NPU
SqueezeNet-1.1	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.281 ms	0 - 30 MB	NPU
SqueezeNet-1.1	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.383 ms	0 - 1 MB	NPU
SqueezeNet-1.1	ONNX	float	Qualcomm® QCS9075	0.61 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	float	Snapdragon® 8 Elite Gen 5 Mobile	0.177 ms	0 - 23 MB	NPU
SqueezeNet-1.1	ONNX	float	Snapdragon® X2 Elite	0.214 ms	0 - 0 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® X Elite	0.486 ms	0 - 0 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.271 ms	0 - 31 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Qualcomm® QCS6490	3.618 ms	5 - 9 MB	CPU
SqueezeNet-1.1	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.375 ms	0 - 3 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Qualcomm® QCS9075	0.495 ms	0 - 3 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Qualcomm® QCM6690	3.1 ms	0 - 7 MB	CPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.235 ms	0 - 21 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	2.202 ms	0 - 7 MB	CPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.214 ms	0 - 25 MB	NPU
SqueezeNet-1.1	ONNX	w8a8	Snapdragon® X2 Elite	0.217 ms	0 - 0 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Snapdragon® X Elite	0.807 ms	1 - 1 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.448 ms	0 - 31 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	2.046 ms	1 - 23 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.653 ms	1 - 2 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® SA8775P	0.938 ms	1 - 22 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® QCS9075	0.871 ms	1 - 3 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	1.267 ms	0 - 33 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® SA7255P	2.046 ms	1 - 23 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Qualcomm® SA8295P	1.135 ms	0 - 18 MB	NPU
SqueezeNet-1.1	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.332 ms	1 - 21 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	float	Snapdragon® X2 Elite	0.36 ms	1 - 1 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® X Elite	0.48 ms	0 - 0 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.266 ms	0 - 30 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® QCS6490	1.069 ms	0 - 2 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	0.905 ms	0 - 21 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.375 ms	0 - 1 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® SA8775P	0.551 ms	0 - 22 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® QCS9075	0.447 ms	0 - 2 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® QCM6690	1.448 ms	0 - 19 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.436 ms	0 - 30 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® SA7255P	0.905 ms	0 - 21 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Qualcomm® SA8295P	0.708 ms	0 - 18 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.182 ms	0 - 19 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.373 ms	0 - 20 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.15 ms	0 - 22 MB	NPU
SqueezeNet-1.1	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.246 ms	0 - 0 MB	NPU
SqueezeNet-1.1	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.455 ms	0 - 33 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® QCS8275 (Proxy)	2.027 ms	0 - 24 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® QCS8550 (Proxy)	0.663 ms	0 - 1 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® SA8775P	0.967 ms	0 - 24 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® QCS9075	0.873 ms	0 - 5 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® QCS8450 (Proxy)	1.271 ms	0 - 34 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® SA7255P	2.027 ms	0 - 24 MB	NPU
SqueezeNet-1.1	TFLITE	float	Qualcomm® SA8295P	1.146 ms	0 - 21 MB	NPU
SqueezeNet-1.1	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.331 ms	0 - 27 MB	NPU
SqueezeNet-1.1	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.242 ms	0 - 27 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.143 ms	0 - 29 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® QCS6490	0.541 ms	0 - 3 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	0.607 ms	0 - 21 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.198 ms	0 - 2 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® SA8775P	0.367 ms	0 - 21 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® QCS9075	0.265 ms	0 - 3 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® QCM6690	0.933 ms	0 - 19 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.256 ms	0 - 30 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Qualcomm® SA7255P	0.607 ms	0 - 21 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	0.106 ms	0 - 19 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.199 ms	0 - 19 MB	NPU
SqueezeNet-1.1	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.095 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