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 | 3.126 ms | 0 - 211 MB | NPU |
| YOLOv11-Segmentation | ONNX | float | Snapdragon® X2 Elite | 3.865 ms | 207 - 207 MB | NPU |
| YOLOv11-Segmentation | ONNX | float | Snapdragon® X Elite | 7.314 ms | 145 - 145 MB | NPU |
| YOLOv11-Segmentation | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 6.114 ms | 17 - 247 MB | NPU |
| YOLOv11-Segmentation | ONNX | float | Qualcomm® QCS8550 (Proxy) | 7.831 ms | 13 - 55 MB | NPU |
| YOLOv11-Segmentation | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.808 ms | 12 - 207 MB | NPU |
| YOLOv11-Segmentation | ONNX | float | Qualcomm® QCS9075 | 8.236 ms | 14 - 62 MB | NPU |
| YOLOv11-Segmentation | ONNX | float | Qualcomm® QCS8750 | 4.808 ms | 12 - 207 MB | NPU |
| YOLOv11-Segmentation | ONNX | float | Qualcomm® QCS7181 | 7.314 ms | 145 - 145 MB | NPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.538 ms | 0 - 100 MB | NPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Snapdragon® X2 Elite | 2.764 ms | 210 - 210 MB | NPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Snapdragon® X Elite | 6.323 ms | 179 - 179 MB | NPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.785 ms | 6 - 239 MB | NPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Qualcomm® QCS6490 | 413.559 ms | 165 - 170 MB | CPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 6.048 ms | 6 - 20 MB | NPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Qualcomm® QCM6690 | 219.286 ms | 102 - 112 MB | CPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 196.972 ms | 170 - 180 MB | CPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 2.892 ms | 2 - 103 MB | NPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Qualcomm® QCS9075 | 7.405 ms | 6 - 53 MB | NPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Qualcomm® QCS7790 | 196.972 ms | 170 - 180 MB | CPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Qualcomm® QCS8750 | 2.892 ms | 2 - 103 MB | NPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Qualcomm® QCS7181 | 6.323 ms | 179 - 179 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.134 ms | 5 - 200 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Snapdragon® X2 Elite | 2.93 ms | 5 - 5 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Snapdragon® X Elite | 5.417 ms | 5 - 5 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.624 ms | 0 - 209 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Qualcomm® QCS8275 | 16.314 ms | 1 - 184 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 4.958 ms | 5 - 109 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Qualcomm® SA8775P | 6.678 ms | 0 - 185 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Qualcomm® SA8650P | 6.678 ms | 0 - 185 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Qualcomm® SA8255P | 6.678 ms | 0 - 185 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 10.278 ms | 2 - 203 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Qualcomm® SA7255P | 16.314 ms | 1 - 184 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Qualcomm® SA8295P | 10.277 ms | 2 - 174 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.92 ms | 0 - 189 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Qualcomm® QCS9075 | 6.193 ms | 5 - 15 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Qualcomm® QCS8750 | 2.92 ms | 0 - 189 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Qualcomm® QCS7181 | 5.417 ms | 5 - 5 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.915 ms | 2 - 189 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 2.411 ms | 2 - 2 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Snapdragon® X Elite | 5.209 ms | 2 - 2 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.21 ms | 2 - 204 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Qualcomm® QCS8275 | 9.003 ms | 1 - 181 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 4.748 ms | 2 - 4 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8775P | 5.448 ms | 1 - 184 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8650P | 5.448 ms | 1 - 184 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8255P | 5.448 ms | 1 - 184 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 23.013 ms | 2 - 182 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA7255P | 9.003 ms | 1 - 181 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 5.552 ms | 2 - 186 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 2.227 ms | 2 - 188 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 5.605 ms | 1 - 7 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Qualcomm® QCS7790 | 5.552 ms | 2 - 186 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Qualcomm® QCS8750 | 2.227 ms | 2 - 188 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Qualcomm® QCS7181 | 5.209 ms | 2 - 2 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.968 ms | 0 - 103 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3.244 ms | 0 - 110 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Qualcomm® QCS8275 | 15.561 ms | 4 - 86 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 4.416 ms | 4 - 6 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Qualcomm® SA8775P | 6.159 ms | 4 - 87 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Qualcomm® SA8650P | 6.159 ms | 4 - 87 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Qualcomm® SA8255P | 6.159 ms | 4 - 87 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 9.388 ms | 4 - 92 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Qualcomm® SA7255P | 15.561 ms | 4 - 86 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Qualcomm® SA8295P | 9.481 ms | 4 - 61 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.436 ms | 0 - 97 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Qualcomm® QCS9075 | 5.984 ms | 3 - 21 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Qualcomm® QCS8750 | 2.436 ms | 0 - 97 MB | NPU |
License
- The license for the original implementation of YOLOv11-Segmentation can be found here.
References
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.
