Segment-Anything-Model-2: Optimized for Qualcomm Devices

SAM 2, the successor to Meta's Segment Anything Model (SAM), is a cutting-edge tool designed for comprehensive object segmentation in both images and videos. It excels in handling complex visual data through a unified, promptable model architecture that supports real-time processing and zero-shot generalization.

This is based on the implementation of Segment-Anything-Model-2 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
QNN_DLC	float	Universal	QAIRT 2.45	Download
QNN_DLC	w8a8	Universal	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit Segment-Anything-Model-2 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 Segment-Anything-Model-2 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

• Model checkpoint: sam2.1_hiera_t
• Input resolution: 720p (720x1280)
• Number of parameters (encoder): 33.5M
• Model size (encoder) (float): 128 MB
• Number of parameters (decoder): 6.22M
• Model size (decoder) (float): 23.7 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
decoder	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	3.153 ms	17 - 245 MB	NPU
decoder	ONNX	float	Snapdragon® 8 Gen 3 Mobile	4.754 ms	1 - 314 MB	NPU
decoder	ONNX	float	Qualcomm® QCS8550 (Proxy)	6.794 ms	16 - 23 MB	NPU
decoder	ONNX	float	Qualcomm® QCS9075	8.445 ms	16 - 19 MB	NPU
decoder	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	2.59 ms	4 - 190 MB	NPU
decoder	QNN_DLC	float	Snapdragon® 8 Elite Mobile	2.889 ms	4 - 188 MB	NPU
decoder	QNN_DLC	float	Snapdragon® X2 Elite	3.121 ms	16 - 16 MB	NPU
decoder	QNN_DLC	float	Snapdragon® X Elite	5.562 ms	16 - 16 MB	NPU
decoder	QNN_DLC	float	Snapdragon® X Elite	5.562 ms	16 - 16 MB	NPU
decoder	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	3.723 ms	3 - 214 MB	NPU
decoder	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	5.387 ms	16 - 18 MB	NPU
decoder	QNN_DLC	float	Qualcomm® QCS9075	6.744 ms	16 - 34 MB	NPU
decoder	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	10.052 ms	4 - 220 MB	NPU
decoder	QNN_DLC	float	Qualcomm® SA8295P	8.161 ms	0 - 194 MB	NPU
decoder	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	2.889 ms	4 - 188 MB	NPU
decoder	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.889 ms	1 - 109 MB	NPU
decoder	QNN_DLC	w8a8	Snapdragon® 8 Elite Mobile	1.024 ms	1 - 90 MB	NPU
decoder	QNN_DLC	w8a8	Snapdragon® X2 Elite	1.351 ms	4 - 4 MB	NPU
decoder	QNN_DLC	w8a8	Snapdragon® X Elite	2.366 ms	4 - 4 MB	NPU
decoder	QNN_DLC	w8a8	Snapdragon® X Elite	2.366 ms	4 - 4 MB	NPU
decoder	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	1.318 ms	4 - 116 MB	NPU
decoder	QNN_DLC	w8a8	Qualcomm® QCS6490	8.331 ms	3 - 9 MB	NPU
decoder	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	1.994 ms	4 - 122 MB	NPU
decoder	QNN_DLC	w8a8	Qualcomm® QCS9075	2.413 ms	1 - 7 MB	NPU
decoder	QNN_DLC	w8a8	Qualcomm® QCM6690	9.402 ms	4 - 275 MB	NPU
decoder	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	2.588 ms	0 - 110 MB	NPU
decoder	QNN_DLC	w8a8	Qualcomm® SA8295P	2.967 ms	4 - 87 MB	NPU
decoder	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	1.024 ms	1 - 90 MB	NPU
decoder	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	2.52 ms	4 - 211 MB	NPU
decoder	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	2.52 ms	4 - 211 MB	NPU
encoder	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	79.657 ms	2 - 2223 MB	NPU
encoder	ONNX	float	Snapdragon® 8 Gen 3 Mobile	119.374 ms	1 - 1920 MB	NPU
encoder	ONNX	float	Qualcomm® QCS8550 (Proxy)	162.471 ms	0 - 99 MB	NPU
encoder	ONNX	float	Qualcomm® QCS9075	217.885 ms	12 - 27 MB	NPU
encoder	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	87.92 ms	12 - 2381 MB	NPU
encoder	QNN_DLC	float	Snapdragon® 8 Elite Mobile	101.234 ms	12 - 1703 MB	NPU
encoder	QNN_DLC	float	Snapdragon® X2 Elite	95.987 ms	12 - 12 MB	NPU
encoder	QNN_DLC	float	Snapdragon® X Elite	171.373 ms	12 - 12 MB	NPU
encoder	QNN_DLC	float	Snapdragon® X Elite	171.373 ms	12 - 12 MB	NPU
encoder	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	132.265 ms	12 - 1951 MB	NPU
encoder	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	172.918 ms	12 - 15 MB	NPU
encoder	QNN_DLC	float	Qualcomm® QCS9075	227.893 ms	12 - 42 MB	NPU
encoder	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	347.29 ms	12 - 1883 MB	NPU
encoder	QNN_DLC	float	Qualcomm® SA8295P	249.585 ms	0 - 1638 MB	NPU
encoder	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	101.234 ms	12 - 1703 MB	NPU
encoder	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	34.916 ms	3 - 1784 MB	NPU
encoder	QNN_DLC	w8a8	Snapdragon® 8 Elite Mobile	40.707 ms	3 - 1711 MB	NPU
encoder	QNN_DLC	w8a8	Snapdragon® X2 Elite	42.545 ms	3 - 3 MB	NPU
encoder	QNN_DLC	w8a8	Snapdragon® X Elite	79.823 ms	3 - 3 MB	NPU
encoder	QNN_DLC	w8a8	Snapdragon® X Elite	79.823 ms	3 - 3 MB	NPU
encoder	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	54.151 ms	0 - 2214 MB	NPU
encoder	QNN_DLC	w8a8	Qualcomm® QCS6490	631.023 ms	3 - 12 MB	NPU
encoder	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	76.767 ms	3 - 1385 MB	NPU
encoder	QNN_DLC	w8a8	Qualcomm® QCS9075	92.959 ms	5 - 14 MB	NPU
encoder	QNN_DLC	w8a8	Qualcomm® QCM6690	1229.427 ms	3 - 2709 MB	NPU
encoder	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	135.488 ms	3 - 2235 MB	NPU
encoder	QNN_DLC	w8a8	Qualcomm® SA8295P	92.316 ms	0 - 1758 MB	NPU
encoder	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	40.707 ms	3 - 1711 MB	NPU
encoder	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	97.937 ms	3 - 2385 MB	NPU
encoder	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	97.937 ms	3 - 2385 MB	NPU

License

• The license for the original implementation of Segment-Anything-Model-2 can be found here.

References

• SAM 2 Segment Anything in Images and Videos
• 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.