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 2.45, ONNX Runtime 1.25.0	Download
TFLITE	float	Universal	QAIRT 2.45	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® X2 Elite	9.841 ms	182 - 182 MB	NPU
Sequencer2D	ONNX	float	Snapdragon® X Elite	16.903 ms	174 - 174 MB	NPU
Sequencer2D	ONNX	float	Snapdragon® 8 Gen 3 Mobile	11.197 ms	1 - 950 MB	NPU
Sequencer2D	ONNX	float	Snapdragon® 8 Gen 1 Mobile	22.62 ms	1 - 650 MB	NPU
Sequencer2D	ONNX	float	Qualcomm® QCS8550 (Proxy)	16.478 ms	0 - 72 MB	NPU
Sequencer2D	ONNX	float	Qualcomm® QCS8450	22.62 ms	1 - 650 MB	NPU
Sequencer2D	ONNX	float	Snapdragon® 8 Elite Mobile	9.593 ms	1 - 739 MB	NPU
Sequencer2D	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	8.029 ms	1 - 891 MB	NPU
Sequencer2D	ONNX	float	Qualcomm® QCS9075	19.389 ms	1 - 45 MB	NPU
Sequencer2D	ONNX	float	Qualcomm® QCS8750	9.593 ms	1 - 739 MB	NPU
Sequencer2D	ONNX	float	Qualcomm® QCS7181	16.903 ms	174 - 174 MB	NPU
Sequencer2D	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	12.104 ms	0 - 988 MB	NPU
Sequencer2D	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	21.228 ms	0 - 732 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® QCS8275	37.429 ms	0 - 795 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® QCS8550 (Proxy)	18.121 ms	0 - 8 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® SA8775P	194.134 ms	6 - 58 MB	CPU
Sequencer2D	TFLITE	float	Qualcomm® SA8650P	194.134 ms	6 - 58 MB	CPU
Sequencer2D	TFLITE	float	Qualcomm® SA8255P	194.134 ms	6 - 58 MB	CPU
Sequencer2D	TFLITE	float	Qualcomm® QCS8450	21.228 ms	0 - 732 MB	NPU
Sequencer2D	TFLITE	float	Snapdragon® 8 Elite Mobile	9.358 ms	0 - 794 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® SA8295P	20.517 ms	0 - 486 MB	NPU
Sequencer2D	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	7.232 ms	0 - 761 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® SA7255P	37.429 ms	0 - 795 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® QCS9075	20.11 ms	0 - 75 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® QCS8750	9.358 ms	0 - 794 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.