YOLOv11-Segmentation: Optimized for Qualcomm Devices

Ultralytics YOLOv11 is a machine learning model that predicts bounding boxes, segmentation masks and classes of objects in an image.

This is based on the implementation of YOLOv11-Segmentation 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

Due to licensing restrictions, we cannot distribute pre-exported model assets for this model. 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

See our repository for YOLOv11-Segmentation on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

• Model checkpoint: YOLO11N-Seg
• Input resolution: 640x640
• Number of output classes: 80
• Number of parameters: 2.89M
• Model size (float): 11.1 MB
• Model size (w8a16): 11.4 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
YOLOv11-Segmentation	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	2.914 ms	0 - 234 MB	NPU
YOLOv11-Segmentation	ONNX	float	Snapdragon® X2 Elite	3.393 ms	16 - 16 MB	NPU
YOLOv11-Segmentation	ONNX	float	Snapdragon® X Elite	7.168 ms	17 - 17 MB	NPU
YOLOv11-Segmentation	ONNX	float	Snapdragon® 8 Gen 3 Mobile	4.207 ms	16 - 284 MB	NPU
YOLOv11-Segmentation	ONNX	float	Qualcomm® QCS8550 (Proxy)	6.654 ms	11 - 16 MB	NPU
YOLOv11-Segmentation	ONNX	float	Qualcomm® QCS9075	7.833 ms	13 - 16 MB	NPU
YOLOv11-Segmentation	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	3.461 ms	0 - 228 MB	NPU
YOLOv11-Segmentation	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	2.427 ms	0 - 90 MB	NPU
YOLOv11-Segmentation	ONNX	w8a16	Snapdragon® X2 Elite	2.665 ms	6 - 6 MB	NPU
YOLOv11-Segmentation	ONNX	w8a16	Snapdragon® X Elite	6.477 ms	8 - 8 MB	NPU
YOLOv11-Segmentation	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	3.661 ms	1 - 233 MB	NPU
YOLOv11-Segmentation	ONNX	w8a16	Qualcomm® QCS6490	416.127 ms	164 - 169 MB	CPU
YOLOv11-Segmentation	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	5.88 ms	5 - 10 MB	NPU
YOLOv11-Segmentation	ONNX	w8a16	Qualcomm® QCS9075	7.095 ms	6 - 9 MB	NPU
YOLOv11-Segmentation	ONNX	w8a16	Qualcomm® QCM6690	219.193 ms	167 - 176 MB	CPU
YOLOv11-Segmentation	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	2.742 ms	1 - 101 MB	NPU
YOLOv11-Segmentation	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	196.905 ms	99 - 109 MB	CPU
YOLOv11-Segmentation	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.933 ms	0 - 104 MB	NPU
YOLOv11-Segmentation	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	3.15 ms	0 - 114 MB	NPU
YOLOv11-Segmentation	TFLITE	float	Qualcomm® QCS8275 (Proxy)	15.371 ms	4 - 86 MB	NPU
YOLOv11-Segmentation	TFLITE	float	Qualcomm® QCS8550 (Proxy)	4.335 ms	4 - 8 MB	NPU
YOLOv11-Segmentation	TFLITE	float	Qualcomm® SA8775P	6.071 ms	4 - 90 MB	NPU
YOLOv11-Segmentation	TFLITE	float	Qualcomm® QCS9075	5.861 ms	4 - 22 MB	NPU
YOLOv11-Segmentation	TFLITE	float	Qualcomm® QCS8450 (Proxy)	10.077 ms	4 - 211 MB	NPU
YOLOv11-Segmentation	TFLITE	float	Qualcomm® SA7255P	15.371 ms	4 - 86 MB	NPU
YOLOv11-Segmentation	TFLITE	float	Qualcomm® SA8295P	9.371 ms	4 - 177 MB	NPU
YOLOv11-Segmentation	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	2.381 ms	0 - 96 MB	NPU

License

• The license for the original implementation of YOLOv11-Segmentation can be found here.

References

• Ultralytics YOLOv11 Docs: Instance Segmentation
• 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.