YOLO26-Pose: Optimized for Qualcomm Devices
Ultralytics YOLO26-Pose is a machine learning model that predicts human body keypoints and bounding boxes in an image.
This is based on the implementation of YOLO26-Pose 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-Pose on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.pose_estimation
Model Stats:
- Model checkpoint: YOLO26-N-Pose
- Input resolution: 640x640
- Number of parameters: 2.97M
- Model size (float): 11.4 MB
Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| YOLO26-Pose | ONNX | float | Snapdragon® X2 Elite | 4.709 ms | 9 - 9 MB | NPU |
| YOLO26-Pose | ONNX | float | Snapdragon® X Elite | 10.175 ms | 11 - 11 MB | NPU |
| YOLO26-Pose | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 6.883 ms | 9 - 215 MB | NPU |
| YOLO26-Pose | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 17.953 ms | 9 - 229 MB | NPU |
| YOLO26-Pose | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 9.928 ms | 0 - 145 MB | NPU |
| YOLO26-Pose | ONNX | float | Qualcomm® QCS8450 | 17.953 ms | 9 - 229 MB | NPU |
| YOLO26-Pose | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 14.482 ms | 6 - 9 MB | NPU |
| YOLO26-Pose | ONNX | float | Snapdragon® 8 Elite Mobile | 4.752 ms | 4 - 184 MB | NPU |
| YOLO26-Pose | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.386 ms | 5 - 189 MB | NPU |
| YOLO26-Pose | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 4.752 ms | 4 - 184 MB | NPU |
| YOLO26-Pose | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 10.175 ms | 11 - 11 MB | NPU |
| YOLO26-Pose | ONNX | w8a16 | Snapdragon® X2 Elite | 2.631 ms | 4 - 4 MB | NPU |
| YOLO26-Pose | ONNX | w8a16 | Snapdragon® X Elite | 6.677 ms | 3 - 3 MB | NPU |
| YOLO26-Pose | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.823 ms | 0 - 229 MB | NPU |
| YOLO26-Pose | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 7.949 ms | 4 - 238 MB | NPU |
| YOLO26-Pose | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 18.388 ms | 3 - 6 MB | NPU |
| YOLO26-Pose | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.283 ms | 3 - 135 MB | NPU |
| YOLO26-Pose | ONNX | w8a16 | Qualcomm® QCS8450 | 7.949 ms | 4 - 238 MB | NPU |
| YOLO26-Pose | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 2.826 ms | 0 - 89 MB | NPU |
| YOLO26-Pose | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 6.85 ms | 3 - 6 MB | NPU |
| YOLO26-Pose | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 33.381 ms | 4 - 211 MB | NPU |
| YOLO26-Pose | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.478 ms | 0 - 93 MB | NPU |
| YOLO26-Pose | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.208 ms | 4 - 217 MB | NPU |
| YOLO26-Pose | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 10.208 ms | 4 - 217 MB | NPU |
| YOLO26-Pose | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.826 ms | 0 - 89 MB | NPU |
| YOLO26-Pose | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 6.677 ms | 3 - 3 MB | NPU |
| YOLO26-Pose | QNN_DLC | float | Snapdragon® X2 Elite | 3.39 ms | 5 - 5 MB | NPU |
| YOLO26-Pose | QNN_DLC | float | Snapdragon® X Elite | 6.292 ms | 5 - 5 MB | NPU |
| YOLO26-Pose | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 4.16 ms | 5 - 197 MB | NPU |
| YOLO26-Pose | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 10.263 ms | 5 - 215 MB | NPU |
| YOLO26-Pose | QNN_DLC | float | Qualcomm® QCS8275 | 16.738 ms | 0 - 166 MB | NPU |
| YOLO26-Pose | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.788 ms | 5 - 6 MB | NPU |
| YOLO26-Pose | QNN_DLC | float | Qualcomm® SA8775P | 7.264 ms | 1 - 168 MB | NPU |
| YOLO26-Pose | QNN_DLC | float | Qualcomm® SA8650P | 7.264 ms | 1 - 168 MB | NPU |
| YOLO26-Pose | QNN_DLC | float | Qualcomm® SA8255P | 7.264 ms | 1 - 168 MB | NPU |
| YOLO26-Pose | QNN_DLC | float | Qualcomm® QCS8450 | 10.263 ms | 5 - 215 MB | NPU |
| YOLO26-Pose | QNN_DLC | float | Qualcomm® SA8295P | 10.546 ms | 0 - 185 MB | NPU |
| YOLO26-Pose | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 7.004 ms | 5 - 13 MB | NPU |
| YOLO26-Pose | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 3.091 ms | 0 - 159 MB | NPU |
| YOLO26-Pose | QNN_DLC | float | Qualcomm® SA7255P | 16.738 ms | 0 - 166 MB | NPU |
| YOLO26-Pose | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.621 ms | 5 - 194 MB | NPU |
| YOLO26-Pose | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 3.091 ms | 0 - 159 MB | NPU |
| YOLO26-Pose | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 6.292 ms | 5 - 5 MB | NPU |
| YOLO26-Pose | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 2.743 ms | 2 - 2 MB | NPU |
| YOLO26-Pose | QNN_DLC | w8a16 | Snapdragon® X Elite | 5.447 ms | 2 - 2 MB | NPU |
| YOLO26-Pose | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.229 ms | 2 - 216 MB | NPU |
| YOLO26-Pose | QNN_DLC | w8a16 | Qualcomm® QCS8275 | 9.128 ms | 0 - 185 MB | NPU |
| YOLO26-Pose | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.906 ms | 2 - 4 MB | NPU |
| YOLO26-Pose | QNN_DLC | w8a16 | Qualcomm® SA8775P | 5.668 ms | 0 - 185 MB | NPU |
| YOLO26-Pose | QNN_DLC | w8a16 | Qualcomm® SA8650P | 5.668 ms | 0 - 185 MB | NPU |
| YOLO26-Pose | QNN_DLC | w8a16 | Qualcomm® SA8255P | 5.668 ms | 0 - 185 MB | NPU |
| YOLO26-Pose | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 2.597 ms | 2 - 189 MB | NPU |
| YOLO26-Pose | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 5.406 ms | 1 - 6 MB | NPU |
| YOLO26-Pose | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 24.858 ms | 2 - 190 MB | NPU |
| YOLO26-Pose | QNN_DLC | w8a16 | Qualcomm® SA7255P | 9.128 ms | 0 - 185 MB | NPU |
| YOLO26-Pose | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.332 ms | 2 - 201 MB | NPU |
| YOLO26-Pose | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 6.052 ms | 3 - 198 MB | NPU |
| YOLO26-Pose | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 6.052 ms | 3 - 198 MB | NPU |
| YOLO26-Pose | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.597 ms | 2 - 189 MB | NPU |
| YOLO26-Pose | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 5.447 ms | 2 - 2 MB | NPU |
| YOLO26-Pose | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.36 ms | 2 - 224 MB | NPU |
| YOLO26-Pose | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 14.374 ms | 2 - 231 MB | NPU |
| YOLO26-Pose | TFLITE | float | Qualcomm® QCS8275 | 18.516 ms | 2 - 190 MB | NPU |
| YOLO26-Pose | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.693 ms | 2 - 4 MB | NPU |
| YOLO26-Pose | TFLITE | float | Qualcomm® SA8775P | 9.197 ms | 2 - 191 MB | NPU |
| YOLO26-Pose | TFLITE | float | Qualcomm® SA8650P | 9.197 ms | 2 - 191 MB | NPU |
| YOLO26-Pose | TFLITE | float | Qualcomm® SA8255P | 9.197 ms | 2 - 191 MB | NPU |
| YOLO26-Pose | TFLITE | float | Qualcomm® QCS8450 | 14.374 ms | 2 - 231 MB | NPU |
| YOLO26-Pose | TFLITE | float | Qualcomm® SA8295P | 12.595 ms | 2 - 205 MB | NPU |
| YOLO26-Pose | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 8.87 ms | 1 - 25 MB | NPU |
| YOLO26-Pose | TFLITE | float | Snapdragon® 8 Elite Mobile | 3.844 ms | 0 - 181 MB | NPU |
| YOLO26-Pose | TFLITE | float | Qualcomm® SA7255P | 18.516 ms | 2 - 190 MB | NPU |
| YOLO26-Pose | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.255 ms | 0 - 188 MB | NPU |
| YOLO26-Pose | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 3.844 ms | 0 - 181 MB | NPU |
License
- The license for the original implementation of YOLO26-Pose can be found here.
References
Community
- Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
- For questions or feedback please reach out to us.
