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 1.24.3	Download
ONNX	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	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® 8 Elite Gen 5 Mobile	7.903 ms	0 - 1367 MB	NPU
Sequencer2D	ONNX	float	Snapdragon® 8 Elite Mobile	9.85 ms	1 - 1045 MB	NPU
Sequencer2D	ONNX	float	Snapdragon® X2 Elite	9.787 ms	61 - 61 MB	NPU
Sequencer2D	ONNX	float	Snapdragon® X Elite	16.983 ms	59 - 59 MB	NPU
Sequencer2D	ONNX	float	Snapdragon® X Elite	16.983 ms	59 - 59 MB	NPU
Sequencer2D	ONNX	float	Snapdragon® 8 Gen 3 Mobile	11.154 ms	0 - 2275 MB	NPU
Sequencer2D	ONNX	float	Qualcomm® QCS8550 (Proxy)	15.928 ms	0 - 75 MB	NPU
Sequencer2D	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	9.85 ms	1 - 1045 MB	NPU
Sequencer2D	ONNX	float	Qualcomm® QCS9075	19.89 ms	0 - 4 MB	NPU
Sequencer2D	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	8.064 ms	0 - 728 MB	NPU
Sequencer2D	ONNX	w8a16	Snapdragon® 8 Elite Mobile	9.987 ms	0 - 703 MB	NPU
Sequencer2D	ONNX	w8a16	Snapdragon® X2 Elite	9.933 ms	45 - 45 MB	NPU
Sequencer2D	ONNX	w8a16	Snapdragon® X Elite	18.133 ms	43 - 43 MB	NPU
Sequencer2D	ONNX	w8a16	Snapdragon® X Elite	18.133 ms	43 - 43 MB	NPU
Sequencer2D	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	11.514 ms	0 - 886 MB	NPU
Sequencer2D	ONNX	w8a16	Qualcomm® QCS6490	623.44 ms	46 - 52 MB	CPU
Sequencer2D	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	17.513 ms	0 - 69 MB	NPU
Sequencer2D	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	9.987 ms	0 - 703 MB	NPU
Sequencer2D	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	299.44 ms	77 - 90 MB	CPU
Sequencer2D	ONNX	w8a16	Qualcomm® QCM6690	309.487 ms	47 - 63 MB	CPU
Sequencer2D	ONNX	w8a16	Qualcomm® QCS9075	20.06 ms	0 - 3 MB	NPU
Sequencer2D	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	299.44 ms	77 - 90 MB	CPU
Sequencer2D	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	7.21 ms	0 - 755 MB	NPU
Sequencer2D	TFLITE	float	Snapdragon® 8 Elite Mobile	9.421 ms	0 - 791 MB	NPU
Sequencer2D	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	11.852 ms	55 - 1042 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® QCS8550 (Proxy)	16.879 ms	0 - 8 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® SA8775P	19.058 ms	0 - 795 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® SA8775P	19.058 ms	0 - 795 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® SA8775P	19.058 ms	0 - 795 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® SA7255P	37.27 ms	0 - 795 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® QCS8450 (Proxy)	21.227 ms	0 - 725 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® SA8295P	20.563 ms	0 - 485 MB	NPU
Sequencer2D	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	9.421 ms	0 - 791 MB	NPU
Sequencer2D	TFLITE	float	Qualcomm® QCS9075	20.116 ms	0 - 75 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.