--- library_name: pytorch license: other tags: - real_time - android pipeline_tag: image-segmentation --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolov11_seg/web-assets/model_demo.png) # 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](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/yolo/segment). This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/yolov11_seg) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary). Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) 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](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/yolov11_seg) 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](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/yolov11_seg) 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 | 2.908 ms | 0 - 234 MB | NPU | YOLOv11-Segmentation | ONNX | float | Snapdragon® X2 Elite | 3.42 ms | 16 - 16 MB | NPU | YOLOv11-Segmentation | ONNX | float | Snapdragon® X Elite | 7.175 ms | 17 - 17 MB | NPU | YOLOv11-Segmentation | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 4.199 ms | 14 - 281 MB | NPU | YOLOv11-Segmentation | ONNX | float | Qualcomm® QCS8550 (Proxy) | 6.647 ms | 11 - 15 MB | NPU | YOLOv11-Segmentation | ONNX | float | Qualcomm® QCS9075 | 7.83 ms | 12 - 15 MB | NPU | YOLOv11-Segmentation | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.468 ms | 12 - 237 MB | NPU | YOLOv11-Segmentation | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.441 ms | 0 - 89 MB | NPU | YOLOv11-Segmentation | ONNX | w8a16 | Snapdragon® X2 Elite | 2.679 ms | 6 - 6 MB | NPU | YOLOv11-Segmentation | ONNX | w8a16 | Snapdragon® X Elite | 6.435 ms | 8 - 8 MB | NPU | YOLOv11-Segmentation | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.661 ms | 8 - 240 MB | NPU | YOLOv11-Segmentation | ONNX | w8a16 | Qualcomm® QCS6490 | 436.77 ms | 164 - 169 MB | CPU | YOLOv11-Segmentation | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 5.908 ms | 5 - 11 MB | NPU | YOLOv11-Segmentation | ONNX | w8a16 | Qualcomm® QCS9075 | 7.164 ms | 6 - 9 MB | NPU | YOLOv11-Segmentation | ONNX | w8a16 | Qualcomm® QCM6690 | 217.954 ms | 182 - 191 MB | CPU | YOLOv11-Segmentation | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 2.757 ms | 0 - 83 MB | NPU | YOLOv11-Segmentation | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 197.306 ms | 165 - 175 MB | CPU | YOLOv11-Segmentation | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.917 ms | 0 - 105 MB | NPU | YOLOv11-Segmentation | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3.155 ms | 0 - 114 MB | NPU | YOLOv11-Segmentation | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 15.405 ms | 4 - 85 MB | NPU | YOLOv11-Segmentation | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 4.331 ms | 4 - 13 MB | NPU | YOLOv11-Segmentation | TFLITE | float | Qualcomm® SA8775P | 6.047 ms | 4 - 90 MB | NPU | YOLOv11-Segmentation | TFLITE | float | Qualcomm® QCS9075 | 5.859 ms | 4 - 22 MB | NPU | YOLOv11-Segmentation | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 10.079 ms | 4 - 208 MB | NPU | YOLOv11-Segmentation | TFLITE | float | Qualcomm® SA7255P | 15.405 ms | 4 - 85 MB | NPU | YOLOv11-Segmentation | TFLITE | float | Qualcomm® SA8295P | 9.314 ms | 4 - 177 MB | NPU | YOLOv11-Segmentation | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.366 ms | 0 - 85 MB | NPU ## License * The license for the original implementation of YOLOv11-Segmentation can be found [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE). ## References * [Ultralytics YOLOv11 Docs: Instance Segmentation](https://docs.ultralytics.com/tasks/segment/) * [Source Model Implementation](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/yolo/segment) ## Community * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI. * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).