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 | 3.131 ms | 0 - 218 MB | NPU |
| YOLOv11-Segmentation | ONNX | float | Snapdragon® 8 Elite Mobile | 4.802 ms | 11 - 209 MB | NPU |
| YOLOv11-Segmentation | ONNX | float | Snapdragon® X2 Elite | 3.88 ms | 16 - 16 MB | NPU |
| YOLOv11-Segmentation | ONNX | float | Snapdragon® X Elite | 7.641 ms | 17 - 17 MB | NPU |
| YOLOv11-Segmentation | ONNX | float | Snapdragon® X Elite | 7.641 ms | 17 - 17 MB | NPU |
| YOLOv11-Segmentation | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 6.08 ms | 16 - 253 MB | NPU |
| YOLOv11-Segmentation | ONNX | float | Qualcomm® QCS8550 (Proxy) | 7.744 ms | 11 - 16 MB | NPU |
| YOLOv11-Segmentation | ONNX | float | Qualcomm® QCS9075 | 8.212 ms | 13 - 16 MB | NPU |
| YOLOv11-Segmentation | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.802 ms | 11 - 209 MB | NPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.541 ms | 0 - 90 MB | NPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 2.894 ms | 1 - 92 MB | NPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Snapdragon® X2 Elite | 2.743 ms | 6 - 6 MB | NPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Snapdragon® X Elite | 6.631 ms | 8 - 8 MB | NPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Snapdragon® X Elite | 6.631 ms | 8 - 8 MB | NPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.764 ms | 8 - 240 MB | NPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Qualcomm® QCS6490 | 439.737 ms | 164 - 169 MB | CPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 6.036 ms | 5 - 10 MB | NPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Qualcomm® QCS9075 | 7.369 ms | 7 - 10 MB | NPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Qualcomm® QCM6690 | 217.578 ms | 108 - 118 MB | CPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 2.894 ms | 1 - 92 MB | NPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 196.206 ms | 166 - 176 MB | CPU |
| YOLOv11-Segmentation | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 196.206 ms | 166 - 176 MB | CPU |
| YOLOv11-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.156 ms | 4 - 197 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 2.925 ms | 0 - 185 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Snapdragon® X2 Elite | 2.973 ms | 5 - 5 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Snapdragon® X Elite | 5.353 ms | 5 - 5 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Snapdragon® X Elite | 5.353 ms | 5 - 5 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.617 ms | 5 - 215 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 16.276 ms | 1 - 184 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 4.935 ms | 5 - 47 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Qualcomm® SA8775P | 6.68 ms | 1 - 187 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Qualcomm® SA8775P | 6.68 ms | 1 - 187 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Qualcomm® SA8775P | 6.68 ms | 1 - 187 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Qualcomm® QCS9075 | 6.19 ms | 5 - 15 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 10.395 ms | 5 - 206 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Qualcomm® SA7255P | 16.276 ms | 1 - 184 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Qualcomm® SA8295P | 10.252 ms | 0 - 173 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.925 ms | 0 - 185 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.92 ms | 2 - 189 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 2.222 ms | 2 - 182 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 2.443 ms | 2 - 2 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Snapdragon® X Elite | 5.199 ms | 2 - 2 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Snapdragon® X Elite | 5.199 ms | 2 - 2 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.2 ms | 2 - 206 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 8.988 ms | 1 - 181 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 4.75 ms | 2 - 19 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8775P | 5.44 ms | 1 - 184 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8775P | 5.44 ms | 1 - 184 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8775P | 5.44 ms | 1 - 184 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 5.611 ms | 1 - 7 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 25.939 ms | 2 - 184 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA7255P | 8.988 ms | 1 - 181 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 2.222 ms | 2 - 182 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 5.386 ms | 2 - 187 MB | NPU |
| YOLOv11-Segmentation | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 5.386 ms | 2 - 187 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.97 ms | 0 - 103 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Snapdragon® 8 Elite Mobile | 2.443 ms | 0 - 88 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3.206 ms | 0 - 112 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 15.54 ms | 4 - 85 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 4.465 ms | 4 - 6 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Qualcomm® SA8775P | 6.144 ms | 4 - 87 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Qualcomm® SA8775P | 6.144 ms | 4 - 87 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Qualcomm® SA8775P | 6.144 ms | 4 - 87 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Qualcomm® QCS9075 | 5.993 ms | 4 - 22 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 9.43 ms | 4 - 88 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Qualcomm® SA7255P | 15.54 ms | 4 - 85 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Qualcomm® SA8295P | 9.442 ms | 4 - 62 MB | NPU |
| YOLOv11-Segmentation | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.443 ms | 0 - 88 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.
