EfficientViT-b2-cls: Optimized for Qualcomm Devices

EfficientViT 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 EfficientViT-b2-cls 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 EfficientViT-b2-cls 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 EfficientViT-b2-cls 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: 24.3M
• Model size (float): 92.9 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
EfficientViT-b2-cls	ONNX	float	Snapdragon® X2 Elite	2.526 ms	49 - 49 MB	NPU
EfficientViT-b2-cls	ONNX	float	Snapdragon® X Elite	5.943 ms	49 - 49 MB	NPU
EfficientViT-b2-cls	ONNX	float	Snapdragon® 8 Gen 3 Mobile	3.59 ms	0 - 180 MB	NPU
EfficientViT-b2-cls	ONNX	float	Qualcomm® QCS8550 (Proxy)	5.129 ms	0 - 68 MB	NPU
EfficientViT-b2-cls	ONNX	float	Qualcomm® QCS9075	5.799 ms	1 - 4 MB	NPU
EfficientViT-b2-cls	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	2.666 ms	0 - 88 MB	NPU
EfficientViT-b2-cls	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	2.261 ms	0 - 115 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Snapdragon® X2 Elite	2.96 ms	1 - 1 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Snapdragon® X Elite	5.964 ms	1 - 1 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	3.752 ms	0 - 164 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	12.936 ms	1 - 89 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	5.316 ms	1 - 3 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Qualcomm® QCS9075	6.13 ms	1 - 3 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	7.104 ms	0 - 163 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	2.757 ms	0 - 93 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	2.334 ms	1 - 93 MB	NPU
EfficientViT-b2-cls	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	3.763 ms	0 - 225 MB	NPU
EfficientViT-b2-cls	TFLITE	float	Qualcomm® QCS8275 (Proxy)	12.938 ms	0 - 148 MB	NPU
EfficientViT-b2-cls	TFLITE	float	Qualcomm® QCS8550 (Proxy)	5.266 ms	0 - 3 MB	NPU
EfficientViT-b2-cls	TFLITE	float	Qualcomm® QCS9075	6.105 ms	0 - 52 MB	NPU
EfficientViT-b2-cls	TFLITE	float	Qualcomm® QCS8450 (Proxy)	7.083 ms	0 - 225 MB	NPU
EfficientViT-b2-cls	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	2.772 ms	0 - 142 MB	NPU
EfficientViT-b2-cls	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	2.326 ms	0 - 153 MB	NPU

License

• The license for the original implementation of EfficientViT-b2-cls can be found here.

References

• EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction
• 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.