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:

  • 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® 8 Elite Gen 5 For Galaxy Mobile 3.546 ms 1 - 171 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® 8 Elite For Galaxy Mobile 3.888 ms 13 - 176 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® X2 Elite 3.604 ms 17 - 17 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® X Elite 7.17 ms 17 - 17 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® 8 Gen 3 Mobile 5.03 ms 18 - 213 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® 8 Gen 1 Mobile 13.545 ms 17 - 231 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® Dragonwing™ IQ-8275 8.045 ms 15 - 19 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 6.954 ms 15 - 22 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® QCS8450 13.545 ms 17 - 231 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® Dragonwing™ IQ-9075 8.21 ms 17 - 20 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® Dragonwing™ IQ-X7181 7.17 ms 17 - 17 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® Dragonwing™ Q-8750 3.888 ms 13 - 176 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 2.426 ms 0 - 99 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.777 ms 1 - 97 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® X2 Elite 2.616 ms 9 - 9 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® X Elite 6.437 ms 7 - 7 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 3.749 ms 8 - 237 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 7.88 ms 8 - 236 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 22.511 ms 8 - 11 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 5.489 ms 8 - 12 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 6.039 ms 6 - 10 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® QCS8450 7.88 ms 8 - 236 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 6.571 ms 8 - 11 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 6.437 ms 7 - 7 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 30.514 ms 0 - 201 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 7.95 ms 8 - 214 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 2.777 ms 1 - 97 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 7.95 ms 8 - 214 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 2.393 ms 5 - 161 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 3.131 ms 5 - 158 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® X2 Elite 3.122 ms 5 - 5 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® X Elite 5.647 ms 5 - 5 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Gen 3 Mobile 3.884 ms 0 - 173 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Gen 1 Mobile 10.379 ms 3 - 200 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 6.634 ms 5 - 17 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 5.233 ms 5 - 6 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA8775P 6.87 ms 0 - 156 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA8650P 6.87 ms 0 - 156 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA8255P 6.87 ms 0 - 156 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® QCS8450 10.379 ms 3 - 200 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 6.661 ms 5 - 16 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 5.647 ms 5 - 5 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® Dragonwing™ Q-8750 3.131 ms 5 - 158 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA7255P 16.805 ms 0 - 153 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA8295P 11.266 ms 0 - 174 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 2.173 ms 2 - 189 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.5 ms 2 - 182 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® X2 Elite 2.681 ms 2 - 2 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® X Elite 5.502 ms 2 - 2 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 3.259 ms 2 - 206 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 4.759 ms 1 - 8 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.9 ms 2 - 4 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® SA8775P 5.607 ms 0 - 181 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® SA8650P 5.607 ms 0 - 181 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® SA8255P 5.607 ms 0 - 181 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 5.383 ms 1 - 8 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 5.502 ms 2 - 2 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 23.956 ms 2 - 184 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 5.375 ms 2 - 182 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 2.5 ms 2 - 182 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® SA7255P 9.37 ms 0 - 180 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 5.375 ms 2 - 182 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 2.702 ms 0 - 159 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 3.431 ms 0 - 162 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Gen 3 Mobile 4.071 ms 4 - 181 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Gen 1 Mobile 10.827 ms 4 - 206 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® Dragonwing™ IQ-8275 7.043 ms 4 - 25 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 5.381 ms 4 - 6 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8775P 7.325 ms 4 - 165 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8650P 7.325 ms 4 - 165 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8255P 7.325 ms 4 - 165 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® QCS8450 10.827 ms 4 - 206 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® Dragonwing™ IQ-9075 7.021 ms 4 - 24 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® Dragonwing™ Q-8750 3.431 ms 0 - 162 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA7255P 17.2 ms 4 - 161 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8295P 11.467 ms 4 - 182 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