YOLO26-Segmentation: Optimized for Qualcomm Devices

Ultralytics YOLO26 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 YOLO26-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 YOLO26-Segmentation on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

  • Input resolution: 640x640
  • Model checkpoint: YOLO26N-Seg
  • Model size (float): 9.29 MB
  • Model size (w8a16): 5.25 MB
  • Number of output classes: 80
  • Number of parameters: 2.7M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
YOLO26-Segmentation ONNX float Snapdragon® X2 Elite 4.101 ms 17 - 17 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® X Elite 8.412 ms 17 - 17 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® 8 Gen 3 Mobile 5.724 ms 17 - 224 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® 8 Gen 1 Mobile 16.364 ms 17 - 244 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® Dragonwing™ IQ-8275 9.174 ms 15 - 19 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 8.15 ms 10 - 22 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® QCS8450 16.364 ms 17 - 244 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® Dragonwing™ IQ-9075 9.68 ms 15 - 18 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® Dragonwing™ IQ-X7181 8.412 ms 17 - 17 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® Dragonwing™ Q-8750 4.436 ms 12 - 190 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® 8 Elite Mobile 4.436 ms 12 - 190 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® 8 Elite Gen 5 Mobile 3.939 ms 12 - 193 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® X2 Elite 2.706 ms 9 - 9 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® X Elite 6.477 ms 7 - 7 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 3.804 ms 0 - 234 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 8.406 ms 8 - 243 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 20.19 ms 8 - 11 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 5.521 ms 8 - 11 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 6.141 ms 8 - 10 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® QCS8450 8.406 ms 8 - 243 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 8.851 ms 8 - 10 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 6.477 ms 7 - 7 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 31.806 ms 9 - 221 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 7.504 ms 8 - 224 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 2.813 ms 0 - 92 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Elite Mobile 2.813 ms 0 - 92 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.512 ms 0 - 96 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 7.504 ms 8 - 224 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® X2 Elite 3.272 ms 5 - 5 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® X Elite 5.492 ms 5 - 5 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Gen 3 Mobile 3.844 ms 5 - 184 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Gen 1 Mobile 10.929 ms 4 - 207 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 6.611 ms 5 - 16 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 16.847 ms 1 - 158 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 5.086 ms 5 - 6 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA8775P 6.86 ms 0 - 162 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA8650P 6.86 ms 0 - 162 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA8255P 6.86 ms 0 - 162 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® QCS8450 10.929 ms 4 - 207 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 6.57 ms 7 - 17 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 5.492 ms 5 - 5 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® Dragonwing™ Q-8750 3.223 ms 5 - 167 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA7255P 16.847 ms 1 - 158 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA8295P 10.958 ms 0 - 174 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Elite Mobile 3.223 ms 5 - 167 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 2.461 ms 5 - 170 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® X2 Elite 2.787 ms 2 - 2 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® X Elite 5.597 ms 2 - 2 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 3.481 ms 0 - 211 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 5.012 ms 1 - 8 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 9.52 ms 1 - 188 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 5.122 ms 2 - 4 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® SA8775P 5.873 ms 2 - 188 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® SA8650P 5.873 ms 2 - 188 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® SA8255P 5.873 ms 2 - 188 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 5.635 ms 1 - 7 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 5.597 ms 2 - 2 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 24.794 ms 2 - 187 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 5.504 ms 2 - 193 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 2.564 ms 0 - 189 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® SA7255P 9.52 ms 1 - 188 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 2.564 ms 0 - 189 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.292 ms 2 - 196 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 5.504 ms 2 - 193 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Gen 3 Mobile 4.094 ms 4 - 193 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Gen 1 Mobile 11.324 ms 4 - 210 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® Dragonwing™ IQ-8275 7.025 ms 4 - 24 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® Dragonwing™ IQ-8275 17.281 ms 4 - 165 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 5.472 ms 4 - 7 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8775P 7.145 ms 4 - 170 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8650P 7.145 ms 4 - 170 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8255P 7.145 ms 4 - 170 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® QCS8450 11.324 ms 4 - 210 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® Dragonwing™ IQ-9075 6.843 ms 4 - 23 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® Dragonwing™ Q-8750 3.19 ms 0 - 169 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA7255P 17.281 ms 4 - 165 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8295P 11.454 ms 4 - 181 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Elite Mobile 3.19 ms 0 - 169 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 2.762 ms 0 - 167 MB NPU

License

  • The license for the original implementation of YOLO26-Segmentation can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support