QuickSRNetLarge: Optimized for Qualcomm Devices
QuickSRNet Large is designed for upscaling images on mobile platforms to sharpen in real-time.
This is based on the implementation of QuickSRNetLarge 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 2.42, ONNX Runtime 1.24.3 | Download |
| ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | Download |
| QNN_DLC | float | 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 QuickSRNetLarge 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 QuickSRNetLarge on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.super_resolution
Model Stats:
- Model checkpoint: quicksrnet_large_3x_checkpoint
- Input resolution: 128x128
- Number of parameters: 436K
- Model size (float): 1.67 MB
- Model size (w8a8): 462 KB
Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| QuickSRNetLarge | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.938 ms | 0 - 23 MB | NPU |
| QuickSRNetLarge | ONNX | float | Snapdragon® 8 Elite Mobile | 1.243 ms | 0 - 20 MB | NPU |
| QuickSRNetLarge | ONNX | float | Snapdragon® X2 Elite | 1.214 ms | 6 - 6 MB | NPU |
| QuickSRNetLarge | ONNX | float | Snapdragon® X Elite | 2.178 ms | 8 - 8 MB | NPU |
| QuickSRNetLarge | ONNX | float | Snapdragon® X Elite | 2.178 ms | 8 - 8 MB | NPU |
| QuickSRNetLarge | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.501 ms | 0 - 37 MB | NPU |
| QuickSRNetLarge | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1.986 ms | 0 - 2 MB | NPU |
| QuickSRNetLarge | ONNX | float | Qualcomm® QCS9075 | 3.522 ms | 8 - 11 MB | NPU |
| QuickSRNetLarge | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.243 ms | 0 - 20 MB | NPU |
| QuickSRNetLarge | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.341 ms | 0 - 27 MB | CPU |
| QuickSRNetLarge | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 0.394 ms | 0 - 23 MB | CPU |
| QuickSRNetLarge | ONNX | w8a8 | Snapdragon® X2 Elite | 0.399 ms | 3 - 3 MB | CPU |
| QuickSRNetLarge | ONNX | w8a8 | Snapdragon® X Elite | 0.886 ms | 3 - 3 MB | CPU |
| QuickSRNetLarge | ONNX | w8a8 | Snapdragon® X Elite | 0.886 ms | 3 - 3 MB | CPU |
| QuickSRNetLarge | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.498 ms | 0 - 35 MB | CPU |
| QuickSRNetLarge | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.76 ms | 0 - 3 MB | CPU |
| QuickSRNetLarge | ONNX | w8a8 | Qualcomm® QCS9075 | 0.965 ms | 0 - 3 MB | CPU |
| QuickSRNetLarge | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.394 ms | 0 - 23 MB | CPU |
| QuickSRNetLarge | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.839 ms | 0 - 26 MB | NPU |
| QuickSRNetLarge | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.038 ms | 0 - 23 MB | NPU |
| QuickSRNetLarge | QNN_DLC | float | Snapdragon® X2 Elite | 1.216 ms | 0 - 0 MB | NPU |
| QuickSRNetLarge | QNN_DLC | float | Snapdragon® X Elite | 2.026 ms | 0 - 0 MB | NPU |
| QuickSRNetLarge | QNN_DLC | float | Snapdragon® X Elite | 2.026 ms | 0 - 0 MB | NPU |
| QuickSRNetLarge | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.287 ms | 0 - 37 MB | NPU |
| QuickSRNetLarge | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 11.868 ms | 0 - 22 MB | NPU |
| QuickSRNetLarge | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 1.824 ms | 0 - 2 MB | NPU |
| QuickSRNetLarge | QNN_DLC | float | Qualcomm® SA8775P | 3.382 ms | 0 - 24 MB | NPU |
| QuickSRNetLarge | QNN_DLC | float | Qualcomm® SA8775P | 3.382 ms | 0 - 24 MB | NPU |
| QuickSRNetLarge | QNN_DLC | float | Qualcomm® SA8775P | 3.382 ms | 0 - 24 MB | NPU |
| QuickSRNetLarge | QNN_DLC | float | Qualcomm® QCS9075 | 3.364 ms | 0 - 5 MB | NPU |
| QuickSRNetLarge | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 3.268 ms | 0 - 38 MB | NPU |
| QuickSRNetLarge | QNN_DLC | float | Qualcomm® SA7255P | 11.868 ms | 0 - 22 MB | NPU |
| QuickSRNetLarge | QNN_DLC | float | Qualcomm® SA8295P | 3.921 ms | 0 - 21 MB | NPU |
| QuickSRNetLarge | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.038 ms | 0 - 23 MB | NPU |
| QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.255 ms | 0 - 27 MB | NPU |
| QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.374 ms | 0 - 24 MB | NPU |
| QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.402 ms | 0 - 0 MB | NPU |
| QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.777 ms | 0 - 0 MB | NPU |
| QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.777 ms | 0 - 0 MB | NPU |
| QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.441 ms | 0 - 33 MB | NPU |
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 2.715 ms | 0 - 2 MB | NPU |
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 2.094 ms | 0 - 23 MB | NPU |
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.645 ms | 0 - 2 MB | NPU |
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.854 ms | 0 - 26 MB | NPU |
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.854 ms | 0 - 26 MB | NPU |
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.854 ms | 0 - 26 MB | NPU |
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 0.855 ms | 0 - 2 MB | NPU |
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 8.331 ms | 0 - 135 MB | NPU |
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.821 ms | 0 - 35 MB | NPU |
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® SA7255P | 2.094 ms | 0 - 23 MB | NPU |
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.37 ms | 0 - 21 MB | NPU |
| QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.374 ms | 0 - 24 MB | NPU |
| QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.91 ms | 0 - 23 MB | NPU |
| QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.91 ms | 0 - 23 MB | NPU |
| QuickSRNetLarge | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.865 ms | 0 - 28 MB | NPU |
| QuickSRNetLarge | TFLITE | float | Snapdragon® 8 Elite Mobile | 1.085 ms | 0 - 25 MB | NPU |
| QuickSRNetLarge | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.451 ms | 0 - 39 MB | NPU |
| QuickSRNetLarge | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 12.202 ms | 3 - 28 MB | NPU |
| QuickSRNetLarge | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 2.136 ms | 0 - 2 MB | NPU |
| QuickSRNetLarge | TFLITE | float | Qualcomm® SA8775P | 3.787 ms | 0 - 27 MB | NPU |
| QuickSRNetLarge | TFLITE | float | Qualcomm® SA8775P | 3.787 ms | 0 - 27 MB | NPU |
| QuickSRNetLarge | TFLITE | float | Qualcomm® SA8775P | 3.787 ms | 0 - 27 MB | NPU |
| QuickSRNetLarge | TFLITE | float | Qualcomm® QCS9075 | 3.701 ms | 3 - 9 MB | NPU |
| QuickSRNetLarge | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 3.495 ms | 0 - 40 MB | NPU |
| QuickSRNetLarge | TFLITE | float | Qualcomm® SA7255P | 12.202 ms | 3 - 28 MB | NPU |
| QuickSRNetLarge | TFLITE | float | Qualcomm® SA8295P | 4.174 ms | 0 - 22 MB | NPU |
| QuickSRNetLarge | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.085 ms | 0 - 25 MB | NPU |
| QuickSRNetLarge | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.281 ms | 0 - 28 MB | NPU |
| QuickSRNetLarge | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 0.387 ms | 0 - 24 MB | NPU |
| QuickSRNetLarge | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.49 ms | 0 - 34 MB | NPU |
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCS6490 | 2.947 ms | 0 - 3 MB | NPU |
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 2.214 ms | 0 - 26 MB | NPU |
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.785 ms | 0 - 66 MB | NPU |
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® SA8775P | 0.995 ms | 0 - 27 MB | NPU |
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® SA8775P | 0.995 ms | 0 - 27 MB | NPU |
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® SA8775P | 0.995 ms | 0 - 27 MB | NPU |
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCS9075 | 0.99 ms | 0 - 3 MB | NPU |
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCM6690 | 8.53 ms | 0 - 137 MB | NPU |
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.915 ms | 0 - 36 MB | NPU |
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® SA7255P | 2.214 ms | 0 - 26 MB | NPU |
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® SA8295P | 1.477 ms | 0 - 23 MB | NPU |
| QuickSRNetLarge | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.387 ms | 0 - 24 MB | NPU |
| QuickSRNetLarge | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.971 ms | 0 - 24 MB | NPU |
| QuickSRNetLarge | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.971 ms | 0 - 24 MB | NPU |
License
- The license for the original implementation of QuickSRNetLarge can be found here.
References
- QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms
- Source Model Implementation
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.
