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® 8 Elite Gen 5 Mobile 3.446 ms 0 - 175 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® X2 Elite 3.787 ms 208 - 208 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® X Elite 6.913 ms 144 - 144 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® 8 Gen 3 Mobile 4.781 ms 17 - 222 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® QCS8550 (Proxy) 6.876 ms 12 - 56 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® 8 Elite For Galaxy Mobile 5.305 ms 13 - 195 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® QCS9075 14.153 ms 15 - 60 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® QCS8750 5.305 ms 13 - 195 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® QCS7181 6.913 ms 144 - 144 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.567 ms 0 - 98 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® X2 Elite 2.765 ms 210 - 210 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® X Elite 6.418 ms 147 - 147 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 3.852 ms 0 - 244 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® QCS6490 439.546 ms 171 - 176 MB CPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® QCS8550 (Proxy) 6.147 ms 5 - 71 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® QCM6690 216.564 ms 171 - 183 MB CPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 195.356 ms 104 - 115 MB CPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.898 ms 2 - 97 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® QCS9075 7.446 ms 6 - 53 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® QCS7790 195.356 ms 104 - 115 MB CPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® QCS8750 2.898 ms 2 - 97 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® QCS7181 6.418 ms 147 - 147 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 2.4 ms 5 - 169 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® X2 Elite 3.221 ms 5 - 5 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® X Elite 5.656 ms 5 - 5 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Gen 3 Mobile 3.788 ms 0 - 186 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® QCS8275 16.663 ms 1 - 158 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® QCS8550 (Proxy) 5.196 ms 5 - 18 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA8775P 6.835 ms 0 - 160 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA8650P 6.835 ms 0 - 160 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA8255P 6.835 ms 0 - 160 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® QCS8450 (Proxy) 10.943 ms 2 - 205 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA7255P 16.663 ms 1 - 158 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA8295P 10.97 ms 0 - 175 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 3.19 ms 5 - 169 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® QCS9075 7.534 ms 5 - 15 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® QCS8750 3.19 ms 5 - 169 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® QCS7181 5.656 ms 5 - 5 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.264 ms 2 - 195 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® X2 Elite 2.73 ms 2 - 2 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® X Elite 5.604 ms 2 - 2 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 3.522 ms 2 - 215 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® QCS8275 9.525 ms 2 - 187 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 5.172 ms 2 - 4 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® SA8775P 5.941 ms 0 - 188 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® SA8650P 5.941 ms 0 - 188 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® SA8255P 5.941 ms 0 - 188 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® QCM6690 25.481 ms 2 - 190 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® SA7255P 9.525 ms 2 - 187 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 5.467 ms 2 - 190 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.551 ms 2 - 193 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® QCS9075 6.068 ms 0 - 6 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® QCS7790 5.467 ms 2 - 190 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® QCS8750 2.551 ms 2 - 193 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® QCS7181 5.604 ms 2 - 2 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 2.647 ms 0 - 168 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Gen 3 Mobile 4.105 ms 4 - 192 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® QCS8275 17.335 ms 4 - 165 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® QCS8550 (Proxy) 5.469 ms 4 - 14 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8775P 7.047 ms 4 - 170 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8650P 7.047 ms 4 - 170 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8255P 7.047 ms 4 - 170 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® QCS8450 (Proxy) 11.489 ms 4 - 212 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA7255P 17.335 ms 4 - 165 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8295P 11.423 ms 4 - 181 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 3.186 ms 0 - 169 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® QCS9075 7.892 ms 3 - 21 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® QCS8750 3.186 ms 0 - 169 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