ConvNext-Tiny: Optimized for Qualcomm Devices
ConvNextTiny is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.
This is based on the implementation of ConvNext-Tiny 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
There are two ways to deploy this model on your device:
Option 1: Download Pre-Exported Models
Below are pre-exported model assets ready for deployment.
| Runtime | Precision | Chipset | SDK Versions | Download |
|---|---|---|---|---|
| ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| ONNX | w8a16 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| QNN_DLC | float | Universal | QAIRT 2.45 | Download |
| QNN_DLC | w8a16 | Universal | QAIRT 2.45 | Download |
| QNN_DLC | w8a8 | Universal | QAIRT 2.45 | Download |
| TFLITE | float | Universal | QAIRT 2.45 | Download |
| TFLITE | w8a8 | Universal | QAIRT 2.45 | Download |
For more device-specific assets and performance metrics, visit ConvNext-Tiny on Qualcomm® AI Hub.
Option 2: Export with Custom Configurations
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
This option is ideal if you need to customize the model beyond the default configuration provided here.
See our repository for ConvNext-Tiny on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.image_classification
Model Stats:
- Input resolution: 224x224
- Model checkpoint: Imagenet
- Model size (float): 109 MB
- Model size (w8a16): 28.9 MB
- Number of parameters: 28.6M
Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| ConvNext-Tiny | ONNX | float | Snapdragon® X2 Elite | 1.347 ms | 2 - 2 MB | NPU |
| ConvNext-Tiny | ONNX | float | Snapdragon® X Elite | 2.708 ms | 57 - 57 MB | NPU |
| ConvNext-Tiny | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.024 ms | 0 - 129 MB | NPU |
| ConvNext-Tiny | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 9.02 ms | 1 - 132 MB | NPU |
| ConvNext-Tiny | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 4.276 ms | 0 - 4 MB | NPU |
| ConvNext-Tiny | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.729 ms | 0 - 66 MB | NPU |
| ConvNext-Tiny | ONNX | float | Qualcomm® QCS8450 | 9.02 ms | 1 - 132 MB | NPU |
| ConvNext-Tiny | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 3.849 ms | 0 - 4 MB | NPU |
| ConvNext-Tiny | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.708 ms | 57 - 57 MB | NPU |
| ConvNext-Tiny | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 1.552 ms | 0 - 76 MB | NPU |
| ConvNext-Tiny | ONNX | float | Snapdragon® 8 Elite Mobile | 1.552 ms | 0 - 76 MB | NPU |
| ConvNext-Tiny | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.296 ms | 0 - 77 MB | NPU |
| ConvNext-Tiny | ONNX | w8a16 | Snapdragon® X2 Elite | 0.996 ms | 1 - 1 MB | NPU |
| ConvNext-Tiny | ONNX | w8a16 | Snapdragon® X Elite | 2.229 ms | 30 - 30 MB | NPU |
| ConvNext-Tiny | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.539 ms | 0 - 131 MB | NPU |
| ConvNext-Tiny | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 3.291 ms | 0 - 132 MB | NPU |
| ConvNext-Tiny | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 9.757 ms | 0 - 3 MB | NPU |
| ConvNext-Tiny | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.164 ms | 0 - 34 MB | NPU |
| ConvNext-Tiny | ONNX | w8a16 | Qualcomm® QCS8450 | 3.291 ms | 0 - 132 MB | NPU |
| ConvNext-Tiny | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 2.365 ms | 0 - 3 MB | NPU |
| ConvNext-Tiny | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 2.229 ms | 30 - 30 MB | NPU |
| ConvNext-Tiny | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 21.82 ms | 0 - 239 MB | NPU |
| ConvNext-Tiny | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 2.595 ms | 0 - 116 MB | NPU |
| ConvNext-Tiny | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 1.14 ms | 0 - 109 MB | NPU |
| ConvNext-Tiny | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 1.14 ms | 0 - 109 MB | NPU |
| ConvNext-Tiny | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.947 ms | 0 - 109 MB | NPU |
| ConvNext-Tiny | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 2.595 ms | 0 - 116 MB | NPU |
| ConvNext-Tiny | ONNX | w8a8 | Snapdragon® X2 Elite | 0.63 ms | 1 - 1 MB | NPU |
| ConvNext-Tiny | ONNX | w8a8 | Snapdragon® X Elite | 1.375 ms | 30 - 30 MB | NPU |
| ConvNext-Tiny | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.964 ms | 0 - 116 MB | NPU |
| ConvNext-Tiny | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 2.134 ms | 0 - 115 MB | NPU |
| ConvNext-Tiny | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 5.714 ms | 0 - 3 MB | NPU |
| ConvNext-Tiny | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.382 ms | 0 - 34 MB | NPU |
| ConvNext-Tiny | ONNX | w8a8 | Qualcomm® QCS8450 | 2.134 ms | 0 - 115 MB | NPU |
| ConvNext-Tiny | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.507 ms | 0 - 3 MB | NPU |
| ConvNext-Tiny | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 1.375 ms | 30 - 30 MB | NPU |
| ConvNext-Tiny | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 10.664 ms | 0 - 87 MB | NPU |
| ConvNext-Tiny | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1.743 ms | 0 - 83 MB | NPU |
| ConvNext-Tiny | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.779 ms | 0 - 81 MB | NPU |
| ConvNext-Tiny | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 0.779 ms | 0 - 81 MB | NPU |
| ConvNext-Tiny | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.719 ms | 0 - 88 MB | NPU |
| ConvNext-Tiny | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.743 ms | 0 - 83 MB | NPU |
| ConvNext-Tiny | QNN_DLC | float | Snapdragon® X2 Elite | 1.975 ms | 1 - 1 MB | NPU |
| ConvNext-Tiny | QNN_DLC | float | Snapdragon® X Elite | 3.699 ms | 1 - 1 MB | NPU |
| ConvNext-Tiny | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.489 ms | 1 - 129 MB | NPU |
| ConvNext-Tiny | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 9.527 ms | 0 - 130 MB | NPU |
| ConvNext-Tiny | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 4.794 ms | 1 - 4 MB | NPU |
| ConvNext-Tiny | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 14.818 ms | 1 - 76 MB | NPU |
| ConvNext-Tiny | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.464 ms | 1 - 2 MB | NPU |
| ConvNext-Tiny | QNN_DLC | float | Qualcomm® SA8775P | 4.799 ms | 1 - 78 MB | NPU |
| ConvNext-Tiny | QNN_DLC | float | Qualcomm® SA8650P | 4.799 ms | 1 - 78 MB | NPU |
| ConvNext-Tiny | QNN_DLC | float | Qualcomm® SA8255P | 4.799 ms | 1 - 78 MB | NPU |
| ConvNext-Tiny | QNN_DLC | float | Qualcomm® QCS8450 | 9.527 ms | 0 - 130 MB | NPU |
| ConvNext-Tiny | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 5.203 ms | 1 - 3 MB | NPU |
| ConvNext-Tiny | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 3.699 ms | 1 - 1 MB | NPU |
| ConvNext-Tiny | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 1.913 ms | 1 - 77 MB | NPU |
| ConvNext-Tiny | QNN_DLC | float | Qualcomm® SA7255P | 14.818 ms | 1 - 76 MB | NPU |
| ConvNext-Tiny | QNN_DLC | float | Qualcomm® SA8295P | 8.762 ms | 1 - 79 MB | NPU |
| ConvNext-Tiny | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.913 ms | 1 - 77 MB | NPU |
| ConvNext-Tiny | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.582 ms | 0 - 80 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 1.582 ms | 0 - 0 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® X Elite | 3.362 ms | 0 - 0 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 2.156 ms | 0 - 123 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 4.259 ms | 0 - 123 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 11.681 ms | 0 - 2 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 3.013 ms | 0 - 3 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 6.822 ms | 0 - 98 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.107 ms | 0 - 2 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® SA8775P | 3.51 ms | 0 - 100 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® SA8650P | 3.51 ms | 0 - 100 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® SA8255P | 3.51 ms | 0 - 100 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 4.259 ms | 0 - 123 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 3.333 ms | 0 - 2 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 3.362 ms | 0 - 0 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 23.421 ms | 0 - 250 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 3.397 ms | 0 - 110 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 1.59 ms | 0 - 102 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® SA7255P | 6.822 ms | 0 - 98 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® SA8295P | 4.738 ms | 0 - 99 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 1.59 ms | 0 - 102 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.286 ms | 0 - 103 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 3.397 ms | 0 - 110 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.969 ms | 0 - 0 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.941 ms | 0 - 0 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.244 ms | 0 - 108 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 2.605 ms | 0 - 105 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 6.774 ms | 0 - 2 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 1.732 ms | 0 - 3 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 3.788 ms | 0 - 70 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.797 ms | 0 - 2 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a8 | Qualcomm® SA8775P | 2.048 ms | 0 - 72 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a8 | Qualcomm® SA8650P | 2.048 ms | 0 - 72 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a8 | Qualcomm® SA8255P | 2.048 ms | 0 - 72 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 2.605 ms | 0 - 105 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.914 ms | 0 - 2 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 1.941 ms | 0 - 0 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 12.08 ms | 0 - 96 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 2.144 ms | 0 - 73 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.96 ms | 0 - 71 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a8 | Qualcomm® SA7255P | 3.788 ms | 0 - 70 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a8 | Qualcomm® SA8295P | 3.025 ms | 0 - 67 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.96 ms | 0 - 71 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.84 ms | 0 - 81 MB | NPU |
| ConvNext-Tiny | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 2.144 ms | 0 - 73 MB | NPU |
| ConvNext-Tiny | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.128 ms | 0 - 129 MB | NPU |
| ConvNext-Tiny | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 8.881 ms | 0 - 124 MB | NPU |
| ConvNext-Tiny | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 4.284 ms | 0 - 60 MB | NPU |
| ConvNext-Tiny | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 14.007 ms | 0 - 73 MB | NPU |
| ConvNext-Tiny | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.824 ms | 0 - 3 MB | NPU |
| ConvNext-Tiny | TFLITE | float | Qualcomm® SA8775P | 4.274 ms | 0 - 75 MB | NPU |
| ConvNext-Tiny | TFLITE | float | Qualcomm® SA8650P | 4.274 ms | 0 - 75 MB | NPU |
| ConvNext-Tiny | TFLITE | float | Qualcomm® SA8255P | 4.274 ms | 0 - 75 MB | NPU |
| ConvNext-Tiny | TFLITE | float | Qualcomm® QCS8450 | 8.881 ms | 0 - 124 MB | NPU |
| ConvNext-Tiny | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 4.05 ms | 0 - 59 MB | NPU |
| ConvNext-Tiny | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 1.593 ms | 0 - 77 MB | NPU |
| ConvNext-Tiny | TFLITE | float | Qualcomm® SA7255P | 14.007 ms | 0 - 73 MB | NPU |
| ConvNext-Tiny | TFLITE | float | Qualcomm® SA8295P | 7.871 ms | 0 - 72 MB | NPU |
| ConvNext-Tiny | TFLITE | float | Snapdragon® 8 Elite Mobile | 1.593 ms | 0 - 77 MB | NPU |
| ConvNext-Tiny | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.334 ms | 0 - 74 MB | NPU |
| ConvNext-Tiny | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.194 ms | 0 - 112 MB | NPU |
| ConvNext-Tiny | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 2.655 ms | 0 - 112 MB | NPU |
| ConvNext-Tiny | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 36.165 ms | 3 - 56 MB | CPU |
| ConvNext-Tiny | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 1.695 ms | 0 - 32 MB | NPU |
| ConvNext-Tiny | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 3.773 ms | 0 - 74 MB | NPU |
| ConvNext-Tiny | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.738 ms | 0 - 3 MB | NPU |
| ConvNext-Tiny | TFLITE | w8a8 | Qualcomm® SA8775P | 2.008 ms | 0 - 76 MB | NPU |
| ConvNext-Tiny | TFLITE | w8a8 | Qualcomm® SA8650P | 2.008 ms | 0 - 76 MB | NPU |
| ConvNext-Tiny | TFLITE | w8a8 | Qualcomm® SA8255P | 2.008 ms | 0 - 76 MB | NPU |
| ConvNext-Tiny | TFLITE | w8a8 | Qualcomm® QCS8450 | 2.655 ms | 0 - 112 MB | NPU |
| ConvNext-Tiny | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.839 ms | 0 - 31 MB | NPU |
| ConvNext-Tiny | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 27.193 ms | 0 - 42 MB | CPU |
| ConvNext-Tiny | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 11.609 ms | 3 - 45 MB | CPU |
| ConvNext-Tiny | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.915 ms | 0 - 77 MB | NPU |
| ConvNext-Tiny | TFLITE | w8a8 | Qualcomm® SA7255P | 3.773 ms | 0 - 74 MB | NPU |
| ConvNext-Tiny | TFLITE | w8a8 | Qualcomm® SA8295P | 2.982 ms | 0 - 70 MB | NPU |
| ConvNext-Tiny | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 0.915 ms | 0 - 77 MB | NPU |
| ConvNext-Tiny | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.778 ms | 0 - 82 MB | NPU |
| ConvNext-Tiny | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 11.609 ms | 3 - 45 MB | CPU |
License
- The license for the original implementation of ConvNext-Tiny 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.
