Sequencer2D: Optimized for Qualcomm Devices

Sequencer2D is a vision transformer model that can classify images from the Imagenet dataset.

This is based on the implementation of Sequencer2D 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 2.50, ONNX Runtime 1.27.1	Download
QNN_DLC	float	Universal	QAIRT 2.50	Download
TFLITE	float	Universal	QAIRT 2.50	Download
TFLITE	w8a8	Universal	QAIRT 2.50	Download

For more device-specific assets and performance metrics, visit Sequencer2D 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 Sequencer2D on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

• Input resolution: 224x224
• Model checkpoint: sequencer2d_s
• Model size (float): 106 MB
• Model size (w8a8): 69.1 MB
• Number of parameters: 27.6M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Sequencer2D	ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	7.501 ms	0 - 755 MB	NPU
Sequencer2D	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	9.331 ms	1 - 733 MB	NPU
Sequencer2D	ONNX	float	Snapdragon® X2 Elite	8.656 ms	2 - 2 MB	NPU
Sequencer2D	ONNX	float	Snapdragon® X Elite	16.069 ms	60 - 60 MB	NPU
Sequencer2D	ONNX	float	Snapdragon® 8 Gen 3 Mobile	11.231 ms	0 - 846 MB	NPU
Sequencer2D	ONNX	float	Snapdragon® 8 Gen 1 Mobile	23.476 ms	1 - 736 MB	NPU
Sequencer2D	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	16.017 ms	1 - 5 MB	NPU
Sequencer2D	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	15.73 ms	0 - 67 MB	NPU
Sequencer2D	ONNX	float	Qualcomm® QCS8450	23.476 ms	1 - 736 MB	NPU
Sequencer2D	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	17.617 ms	1 - 4 MB	NPU
Sequencer2D	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	16.069 ms	60 - 60 MB	NPU
Sequencer2D	ONNX	float	Qualcomm® Dragonwing™ Q-8750	9.331 ms	1 - 733 MB	NPU
Sequencer2D	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	9.827 ms	0 - 913 MB	NPU
Sequencer2D	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	12.353 ms	1 - 870 MB	NPU
Sequencer2D	QNN_DLC	float	Snapdragon® X2 Elite	11.124 ms	1 - 1 MB	NPU
Sequencer2D	QNN_DLC	float	Snapdragon® X Elite	19.84 ms	1 - 1 MB	NPU
Sequencer2D	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	14.632 ms	0 - 994 MB	NPU
Sequencer2D	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	26.858 ms	0 - 865 MB	NPU
Sequencer2D	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	20.237 ms	1 - 3 MB	NPU
Sequencer2D	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	20.187 ms	1 - 4 MB	NPU
Sequencer2D	QNN_DLC	float	Qualcomm® SA8650P	24.036 ms	1 - 901 MB	NPU
Sequencer2D	QNN_DLC	float	Qualcomm® SA8255P	24.036 ms	1 - 901 MB	NPU
Sequencer2D	QNN_DLC	float	Qualcomm® QCS8450	26.858 ms	0 - 865 MB	NPU
Sequencer2D	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	21.806 ms	3 - 5 MB	NPU
Sequencer2D	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	19.84 ms	1 - 1 MB	NPU
Sequencer2D	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	12.353 ms	1 - 870 MB	NPU
Sequencer2D	QNN_DLC	float	Qualcomm® SA8295P	27.351 ms	1 - 740 MB	NPU
Sequencer2D	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	8.542 ms	0 - 899 MB	NPU
Sequencer2D	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	11.503 ms	0 - 866 MB	NPU
Sequencer2D	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	14.612 ms	0 - 995 MB	NPU
Sequencer2D	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	23.814 ms	0 - 727 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	19.297 ms	0 - 79 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	20.288 ms	0 - 10 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® SA8650P	19.048 ms	0 - 796 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® SA8255P	19.048 ms	0 - 796 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® QCS8450	23.814 ms	0 - 727 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	21.314 ms	0 - 79 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	11.503 ms	0 - 866 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® SA8295P	25.087 ms	0 - 596 MB	NPU
Sequencer2D	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	9.051 ms	0 - 962 MB	NPU
Sequencer2D	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	12.575 ms	0 - 904 MB	NPU
Sequencer2D	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	16.23 ms	0 - 1055 MB	NPU
Sequencer2D	TFLITE	w8a8	Snapdragon® 8 Gen 1 Mobile	24.769 ms	0 - 867 MB	NPU
Sequencer2D	TFLITE	w8a8	Qualcomm® Dragonwing™ IQ-8275	20.614 ms	0 - 69 MB	NPU
Sequencer2D	TFLITE	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	22.154 ms	0 - 11 MB	NPU
Sequencer2D	TFLITE	w8a8	Qualcomm® SA8650P	20.405 ms	0 - 862 MB	NPU
Sequencer2D	TFLITE	w8a8	Qualcomm® SA8255P	20.405 ms	0 - 862 MB	NPU
Sequencer2D	TFLITE	w8a8	Qualcomm® QCS8450	24.769 ms	0 - 867 MB	NPU
Sequencer2D	TFLITE	w8a8	Qualcomm® Dragonwing™ IQ-9075	22.739 ms	0 - 68 MB	NPU
Sequencer2D	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-8750	12.575 ms	0 - 904 MB	NPU
Sequencer2D	TFLITE	w8a8	Qualcomm® SA8295P	26.019 ms	0 - 709 MB	NPU

License

• The license for the original implementation of Sequencer2D can be found here.

References

• Sequencer: Deep LSTM for Image Classification
• 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.