MobileSam: Optimized for Qualcomm Devices

Transformer based encoder-decoder where prompts specify what to segment in an image thereby allowing segmentation without the need for additional training. The image encoder generates embeddings and the lightweight decoder operates on the embeddings for point and mask based image segmentation.

This is based on the implementation of MobileSam 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 2.50, ONNX Runtime 1.27.1	Download
QNN_DLC	float	Universal	QAIRT 2.50	Download
TFLITE	float	Universal	QAIRT 2.50	Download

For more device-specific assets and performance metrics, visit MobileSam 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 MobileSam on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

• Input resolution: 720p (720x1280)
• Model checkpoint: vit_t
• Model size (sam_decoder) (float): 23.7 MB
• Model size (sam_encoder) (float): 26.6 MB
• Number of parameters (sam_decoder): 6.16M
• Number of parameters (sam_encoder): 6.95M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
decoder	ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	2.65 ms	1 - 214 MB	NPU
decoder	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	3.059 ms	2 - 213 MB	NPU
decoder	ONNX	float	Snapdragon® X2 Elite	2.75 ms	4 - 4 MB	NPU
decoder	ONNX	float	Snapdragon® X Elite	6.208 ms	11 - 11 MB	NPU
decoder	ONNX	float	Snapdragon® 8 Gen 3 Mobile	4.144 ms	0 - 243 MB	NPU
decoder	ONNX	float	Snapdragon® 8 Gen 1 Mobile	9.469 ms	5 - 230 MB	NPU
decoder	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	6.169 ms	4 - 8 MB	NPU
decoder	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	5.842 ms	0 - 13 MB	NPU
decoder	ONNX	float	Qualcomm® QCS8450	9.469 ms	5 - 230 MB	NPU
decoder	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	6.754 ms	4 - 7 MB	NPU
decoder	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	6.208 ms	11 - 11 MB	NPU
decoder	ONNX	float	Qualcomm® Dragonwing™ Q-8750	3.059 ms	2 - 213 MB	NPU
decoder	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	2.385 ms	4 - 193 MB	NPU
decoder	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	2.795 ms	0 - 182 MB	NPU
decoder	QNN_DLC	float	Snapdragon® X2 Elite	2.802 ms	4 - 4 MB	NPU
decoder	QNN_DLC	float	Snapdragon® X Elite	5.833 ms	4 - 4 MB	NPU
decoder	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	3.705 ms	4 - 220 MB	NPU
decoder	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	7.583 ms	0 - 212 MB	NPU
decoder	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	5.658 ms	4 - 11 MB	NPU
decoder	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	5.344 ms	4 - 18 MB	NPU
decoder	QNN_DLC	float	Qualcomm® SA8650P	6.389 ms	0 - 196 MB	NPU
decoder	QNN_DLC	float	Qualcomm® SA8255P	6.389 ms	0 - 196 MB	NPU
decoder	QNN_DLC	float	Qualcomm® QCS8450	7.583 ms	0 - 212 MB	NPU
decoder	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	6.211 ms	6 - 12 MB	NPU
decoder	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	5.833 ms	4 - 4 MB	NPU
decoder	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	2.795 ms	0 - 182 MB	NPU
decoder	QNN_DLC	float	Qualcomm® SA8295P	7.7 ms	0 - 187 MB	NPU
decoder	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	2.233 ms	0 - 182 MB	NPU
decoder	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	2.605 ms	0 - 178 MB	NPU
decoder	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	3.393 ms	0 - 209 MB	NPU
decoder	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	7.23 ms	0 - 207 MB	NPU
decoder	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	5.25 ms	0 - 20 MB	NPU
decoder	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	4.845 ms	0 - 17 MB	NPU
decoder	TFLITE	float	Qualcomm® SA8650P	5.89 ms	0 - 188 MB	NPU
decoder	TFLITE	float	Qualcomm® SA8255P	5.89 ms	0 - 188 MB	NPU
decoder	TFLITE	float	Qualcomm® QCS8450	7.23 ms	0 - 207 MB	NPU
decoder	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	5.758 ms	0 - 19 MB	NPU
decoder	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	2.605 ms	0 - 178 MB	NPU
decoder	TFLITE	float	Qualcomm® SA8295P	7.191 ms	0 - 210 MB	NPU
encoder	ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	749.116 ms	6 - 1245 MB	NPU
encoder	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	74.715 ms	8 - 1135 MB	NPU
encoder	ONNX	float	Snapdragon® X2 Elite	433.712 ms	12 - 12 MB	NPU
encoder	ONNX	float	Snapdragon® X Elite	980.171 ms	18 - 18 MB	NPU
encoder	ONNX	float	Snapdragon® 8 Gen 3 Mobile	887.804 ms	17 - 1422 MB	NPU
encoder	ONNX	float	Snapdragon® 8 Gen 1 Mobile	210.449 ms	20 - 1167 MB	NPU
encoder	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	1164.38 ms	12 - 16 MB	NPU
encoder	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1143.366 ms	0 - 22 MB	NPU
encoder	ONNX	float	Qualcomm® QCS8450	210.449 ms	20 - 1167 MB	NPU
encoder	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	1081.107 ms	12 - 15 MB	NPU
encoder	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	980.171 ms	18 - 18 MB	NPU
encoder	ONNX	float	Qualcomm® Dragonwing™ Q-8750	74.715 ms	8 - 1135 MB	NPU
encoder	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	640.208 ms	0 - 1427 MB	NPU
encoder	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	678.312 ms	0 - 1297 MB	NPU
encoder	QNN_DLC	float	Snapdragon® X2 Elite	413.828 ms	12 - 12 MB	NPU
encoder	QNN_DLC	float	Snapdragon® X Elite	834.33 ms	12 - 12 MB	NPU
encoder	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	81.021 ms	12 - 1644 MB	NPU
encoder	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	204.136 ms	10 - 1344 MB	NPU
encoder	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	983.872 ms	12 - 31 MB	NPU
encoder	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	968.952 ms	12 - 15 MB	NPU
encoder	QNN_DLC	float	Qualcomm® SA8650P	100.287 ms	1 - 1549 MB	NPU
encoder	QNN_DLC	float	Qualcomm® SA8255P	100.287 ms	1 - 1549 MB	NPU
encoder	QNN_DLC	float	Qualcomm® QCS8450	204.136 ms	10 - 1344 MB	NPU
encoder	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	916.19 ms	12 - 30 MB	NPU
encoder	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	834.33 ms	12 - 12 MB	NPU
encoder	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	678.312 ms	0 - 1297 MB	NPU
encoder	QNN_DLC	float	Qualcomm® SA8295P	247.644 ms	0 - 1100 MB	NPU
encoder	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	499.066 ms	4 - 1409 MB	NPU
encoder	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	537.961 ms	4 - 1315 MB	NPU
encoder	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	604.699 ms	0 - 3328 MB	NPU
encoder	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	269.172 ms	4 - 1289 MB	NPU
encoder	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	784.72 ms	0 - 50 MB	NPU
encoder	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	768.45 ms	0 - 4 MB	NPU
encoder	TFLITE	float	Qualcomm® SA8650P	100.639 ms	0 - 1665 MB	NPU
encoder	TFLITE	float	Qualcomm® SA8255P	100.639 ms	0 - 1665 MB	NPU
encoder	TFLITE	float	Qualcomm® QCS8450	269.172 ms	4 - 1289 MB	NPU
encoder	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	731.358 ms	0 - 49 MB	NPU
encoder	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	537.961 ms	4 - 1315 MB	NPU
encoder	TFLITE	float	Qualcomm® SA8295P	241.465 ms	4 - 1136 MB	NPU

License

• The license for the original implementation of MobileSam can be found here.

References

• Segment Anything
• 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.