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 3.439 ms 0 - 174 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® 8 Elite Mobile 5.312 ms 11 - 194 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® X2 Elite 3.772 ms 16 - 16 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® X Elite 7.279 ms 17 - 17 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® X Elite 7.279 ms 17 - 17 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® 8 Gen 3 Mobile 4.824 ms 15 - 218 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® QCS8550 (Proxy) 6.839 ms 11 - 21 MB NPU
YOLO26-Segmentation ONNX float Qualcomm® QCS9075 14.148 ms 11 - 14 MB NPU
YOLO26-Segmentation ONNX float Snapdragon® 8 Elite For Galaxy Mobile 5.312 ms 11 - 194 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.537 ms 0 - 94 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Elite Mobile 2.872 ms 1 - 95 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® X2 Elite 2.735 ms 6 - 6 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® X Elite 6.767 ms 7 - 7 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® X Elite 6.767 ms 7 - 7 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 3.762 ms 8 - 248 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® QCS6490 432.327 ms 171 - 176 MB CPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® QCS8550 (Proxy) 6.167 ms 6 - 12 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® QCS9075 7.394 ms 8 - 11 MB NPU
YOLO26-Segmentation ONNX w8a16 Qualcomm® QCM6690 217.45 ms 173 - 183 MB CPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.872 ms 1 - 95 MB NPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 193.877 ms 104 - 115 MB CPU
YOLO26-Segmentation ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 193.877 ms 104 - 115 MB CPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 2.398 ms 5 - 169 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Elite Mobile 3.193 ms 5 - 167 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® X2 Elite 3.293 ms 5 - 5 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® X Elite 5.654 ms 5 - 5 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® X Elite 5.654 ms 5 - 5 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Gen 3 Mobile 3.793 ms 5 - 190 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® QCS8550 (Proxy) 5.189 ms 5 - 6 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA8775P 6.862 ms 0 - 161 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA8775P 6.862 ms 0 - 161 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA8775P 6.862 ms 0 - 161 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® QCS9075 7.535 ms 7 - 17 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® QCS8450 (Proxy) 10.966 ms 4 - 208 MB NPU
YOLO26-Segmentation QNN_DLC float Qualcomm® SA8295P 10.987 ms 0 - 175 MB NPU
YOLO26-Segmentation QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 3.193 ms 5 - 167 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.264 ms 2 - 194 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 2.568 ms 2 - 192 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® X2 Elite 2.724 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® X Elite 5.604 ms 2 - 2 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 3.521 ms 2 - 213 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 9.534 ms 1 - 187 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 5.172 ms 2 - 6 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® SA8775P 5.926 ms 0 - 188 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® SA8775P 5.926 ms 0 - 188 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® SA8775P 5.926 ms 0 - 188 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® QCS9075 6.052 ms 4 - 10 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® QCM6690 27.076 ms 2 - 190 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Qualcomm® SA7255P 9.534 ms 1 - 187 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.568 ms 2 - 192 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 5.419 ms 2 - 190 MB NPU
YOLO26-Segmentation QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 5.419 ms 2 - 190 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 2.62 ms 0 - 168 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Elite Mobile 3.186 ms 0 - 161 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Gen 3 Mobile 4.124 ms 3 - 193 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® QCS8275 (Proxy) 17.296 ms 4 - 165 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® QCS8550 (Proxy) 5.477 ms 4 - 14 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8775P 7.042 ms 4 - 170 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8775P 7.042 ms 4 - 170 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8775P 7.042 ms 4 - 170 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® QCS9075 7.903 ms 4 - 23 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® QCS8450 (Proxy) 11.486 ms 2 - 210 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA7255P 17.296 ms 4 - 165 MB NPU
YOLO26-Segmentation TFLITE float Qualcomm® SA8295P 11.413 ms 4 - 181 MB NPU
YOLO26-Segmentation TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 3.186 ms 0 - 161 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