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 5.002 ms 176 - 176 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® X Elite 7.725 ms 176 - 176 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® 8 Gen 3 Mobile 5.483 ms 17 - 211 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® 8 Gen 1 Mobile 16.451 ms 17 - 231 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® QCS8550 (Proxy) 7.899 ms 10 - 27 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® QCS8450 16.451 ms 17 - 231 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® 8 Elite Mobile 5.475 ms 14 - 190 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® 8 Elite Gen 5 Mobile 5.451 ms 13 - 187 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® QCS9075 14.502 ms 17 - 62 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® QCS8750 5.475 ms 14 - 190 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® QCS7181 7.725 ms 176 - 176 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® X2 Elite 2.708 ms 211 - 211 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® X Elite 6.459 ms 178 - 178 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 3.81 ms 0 - 226 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 8.277 ms 8 - 236 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® QCS6490 19.695 ms 6 - 53 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® QCS8550 (Proxy) 6.109 ms 6 - 15 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® QCS8450 8.277 ms 8 - 236 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® QCS9075 7.255 ms 6 - 53 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.48 ms 0 - 92 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Elite Mobile 2.815 ms 0 - 95 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 7.551 ms 8 - 219 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® QCM6690 32.456 ms 0 - 206 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® QCS7790 7.551 ms 8 - 219 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® QCS8750 2.815 ms 0 - 95 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® QCS7181 6.459 ms 178 - 178 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® X2 Elite 3.16 ms 5 - 5 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® X Elite 5.602 ms 5 - 5 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Gen 3 Mobile 3.776 ms 5 - 191 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Gen 1 Mobile 10.933 ms 5 - 208 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® QCS8275 16.708 ms 1 - 158 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® QCS8550 (Proxy) 5.194 ms 5 - 6 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® QCS8450 10.933 ms 5 - 208 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Elite Mobile 3.178 ms 0 - 159 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA8295P 11.008 ms 0 - 175 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 2.437 ms 5 - 169 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA7255P 16.708 ms 1 - 158 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® QCS9075 7.527 ms 5 - 15 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® QCS8750 3.178 ms 0 - 159 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® QCS7181 5.602 ms 5 - 5 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® X2 Elite 2.792 ms 2 - 2 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® X Elite 5.629 ms 2 - 2 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 3.521 ms 0 - 210 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® QCS8275 9.497 ms 2 - 187 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 5.167 ms 2 - 4 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® QCS9075 6.057 ms 0 - 6 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.277 ms 2 - 196 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 2.561 ms 2 - 191 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 5.445 ms 0 - 188 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® QCM6690 26.698 ms 2 - 190 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® SA7255P 9.497 ms 2 - 187 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® QCS7790 5.445 ms 0 - 188 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® QCS8750 2.561 ms 2 - 191 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® QCS7181 5.629 ms 2 - 2 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Gen 3 Mobile 4.115 ms 4 - 194 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Gen 1 Mobile 11.426 ms 4 - 211 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® QCS8275 17.289 ms 4 - 165 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® QCS8550 (Proxy) 5.486 ms 4 - 6 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8775P 30.236 ms 7 - 39 MB GPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8650P 30.236 ms 7 - 39 MB GPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8255P 30.236 ms 7 - 39 MB GPU
YOLO26-Segmentation TFLITE float Qualcomm® QCS8450 11.426 ms 4 - 211 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Elite Mobile 3.193 ms 0 - 162 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8295P 11.395 ms 4 - 181 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 2.661 ms 0 - 168 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA7255P 17.289 ms 4 - 165 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® QCS9075 7.926 ms 3 - 22 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® QCS8750 3.193 ms 0 - 162 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