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 2.42, ONNX Runtime 1.24.1	Download
ONNX	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.17.0	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:

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

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Sequencer2D	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	7.895 ms	0 - 1366 MB	NPU
Sequencer2D	ONNX	float	Snapdragon® X2 Elite	9.803 ms	60 - 60 MB	NPU
Sequencer2D	ONNX	float	Snapdragon® X Elite	17.012 ms	59 - 59 MB	NPU
Sequencer2D	ONNX	float	Snapdragon® 8 Gen 3 Mobile	11.215 ms	0 - 2276 MB	NPU
Sequencer2D	ONNX	float	Qualcomm® QCS8550 (Proxy)	16.011 ms	0 - 80 MB	NPU
Sequencer2D	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	9.844 ms	1 - 1050 MB	NPU
Sequencer2D	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	8.074 ms	0 - 729 MB	NPU
Sequencer2D	ONNX	w8a16	Snapdragon® X2 Elite	9.94 ms	45 - 45 MB	NPU
Sequencer2D	ONNX	w8a16	Snapdragon® X Elite	18.116 ms	43 - 43 MB	NPU
Sequencer2D	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	11.459 ms	0 - 869 MB	NPU
Sequencer2D	ONNX	w8a16	Qualcomm® QCS6490	607.451 ms	46 - 52 MB	CPU
Sequencer2D	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	17.009 ms	0 - 60 MB	NPU
Sequencer2D	ONNX	w8a16	Qualcomm® QCM6690	309.79 ms	47 - 63 MB	CPU
Sequencer2D	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	10.122 ms	0 - 702 MB	NPU
Sequencer2D	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	299.201 ms	46 - 60 MB	CPU
Sequencer2D	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	9.924 ms	0 - 1162 MB	NPU
Sequencer2D	QNN_DLC	float	Snapdragon® X2 Elite	12.496 ms	1 - 1 MB	NPU
Sequencer2D	QNN_DLC	float	Snapdragon® X Elite	21.801 ms	1 - 1 MB	NPU
Sequencer2D	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	14.711 ms	1 - 2258 MB	NPU
Sequencer2D	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	53.756 ms	1 - 976 MB	NPU
Sequencer2D	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	20.327 ms	1 - 3 MB	NPU
Sequencer2D	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	26.444 ms	0 - 846 MB	NPU
Sequencer2D	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	12.414 ms	1 - 1044 MB	NPU
Sequencer2D	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	7.134 ms	0 - 768 MB	NPU
Sequencer2D	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	12.05 ms	0 - 1030 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® QCS8275 (Proxy)	37.899 ms	0 - 794 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® QCS8550 (Proxy)	17.238 ms	0 - 8 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® QCS8450 (Proxy)	21.386 ms	0 - 721 MB	NPU
Sequencer2D	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	9.367 ms	0 - 792 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.