Hugging Face's logo

qualcomm
/
YOLO26-Segmentation

Image Segmentation
PyTorch
real_time
android
Model card Files
xet
 Community

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:

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

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
YOLO26-Segmentation ONNX float Snapdragon® X2 Elite 4.088 ms 17 - 17 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® X Elite 8.266 ms 17 - 17 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® 8 Gen 3 Mobile 5.757 ms 17 - 224 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® 8 Gen 1 Mobile 16.263 ms 17 - 241 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 8.114 ms 10 - 22 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® QCS8450 16.263 ms 17 - 241 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® Dragonwing™ IQ-9075 12.73 ms 15 - 18 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® Dragonwing™ IQ-X7181 8.266 ms 17 - 17 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® Dragonwing™ Q-8750 4.435 ms 15 - 192 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® 8 Elite Mobile 4.435 ms 15 - 192 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® 8 Elite Gen 5 Mobile 3.939 ms 12 - 190 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® X2 Elite 2.939 ms 9 - 9 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® X Elite 6.436 ms 7 - 7 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 3.821 ms 8 - 245 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 8.411 ms 8 - 246 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 20.647 ms 8 - 10 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 6.158 ms 8 - 10 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® QCS8450 8.411 ms 8 - 246 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 6.663 ms 8 - 10 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 6.436 ms 7 - 7 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 2.826 ms 1 - 93 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Elite Mobile 2.826 ms 1 - 93 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.504 ms 0 - 98 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® X2 Elite 3.304 ms 5 - 5 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® X Elite 5.564 ms 5 - 5 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Gen 3 Mobile 3.855 ms 5 - 185 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Gen 1 Mobile 10.943 ms 3 - 206 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® Dragonwing™ QCS8275 16.879 ms 1 - 158 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 5.083 ms 5 - 6 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA8775P 6.827 ms 0 - 160 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA8650P 6.827 ms 0 - 160 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA8255P 6.827 ms 0 - 160 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® QCS8450 10.943 ms 3 - 206 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 6.563 ms 7 - 17 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 5.564 ms 5 - 5 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® Dragonwing™ Q-8750 3.203 ms 0 - 160 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA7255P 16.879 ms 1 - 158 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA8295P 10.967 ms 0 - 175 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Elite Mobile 3.203 ms 0 - 160 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 2.463 ms 5 - 169 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® X2 Elite 2.786 ms 2 - 2 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® X Elite 5.611 ms 2 - 2 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 3.481 ms 2 - 212 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8275 9.495 ms 1 - 188 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 5.138 ms 2 - 5 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® SA8775P 5.89 ms 0 - 187 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® SA8650P 5.89 ms 0 - 187 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® SA8255P 5.89 ms 0 - 187 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 5.617 ms 0 - 6 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 5.611 ms 2 - 2 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 25.212 ms 2 - 186 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 5.455 ms 2 - 194 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 2.563 ms 2 - 192 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® SA7255P 9.495 ms 1 - 188 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 2.563 ms 2 - 192 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.313 ms 2 - 197 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 5.455 ms 2 - 194 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Gen 3 Mobile 4.108 ms 3 - 192 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Gen 1 Mobile 11.336 ms 4 - 212 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® Dragonwing™ QCS8275 17.225 ms 4 - 165 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 5.492 ms 4 - 110 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8775P 7.14 ms 4 - 170 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8650P 7.14 ms 4 - 170 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8255P 7.14 ms 4 - 170 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® QCS8450 11.336 ms 4 - 212 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® Dragonwing™ IQ-9075 8.073 ms 4 - 23 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® Dragonwing™ Q-8750 3.211 ms 0 - 169 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA7255P 17.225 ms 4 - 165 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8295P 11.462 ms 4 - 182 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Elite Mobile 3.211 ms 0 - 169 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 2.767 ms 0 - 165 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
Image Segmentation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support