README.md

---
library_name: pytorch
license: other
tags:
- android
pipeline_tag: image-to-image

---

![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/quicksrnetlarge/web-assets/model_demo.png)

# 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](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/quicksrnet).
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/quicksrnetlarge) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).

Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) 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 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/quicksrnetlarge/releases/v0.55.0/quicksrnetlarge-onnx-float.zip)
| ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/quicksrnetlarge/releases/v0.55.0/quicksrnetlarge-onnx-w8a8.zip)
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/quicksrnetlarge/releases/v0.55.0/quicksrnetlarge-qnn_dlc-float.zip)
| QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/quicksrnetlarge/releases/v0.55.0/quicksrnetlarge-qnn_dlc-w8a8.zip)
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/quicksrnetlarge/releases/v0.55.0/quicksrnetlarge-tflite-float.zip)
| TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/quicksrnetlarge/releases/v0.55.0/quicksrnetlarge-tflite-w8a8.zip)

For more device-specific assets and performance metrics, visit **[QuickSRNetLarge on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/quicksrnetlarge)**.


### Option 2: Export with Custom Configurations

Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/quicksrnetlarge) 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](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/quicksrnetlarge) 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 | 0.934 ms | 0 - 24 MB | NPU
| QuickSRNetLarge | ONNX | float | Snapdragon® X Elite | 2.046 ms | 180 - 180 MB | NPU
| QuickSRNetLarge | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.493 ms | 0 - 39 MB | NPU
| QuickSRNetLarge | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1.974 ms | 0 - 15 MB | NPU
| QuickSRNetLarge | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.255 ms | 0 - 25 MB | NPU
| QuickSRNetLarge | ONNX | float | Qualcomm® QCS9075 | 3.523 ms | 7 - 53 MB | NPU
| QuickSRNetLarge | ONNX | float | Qualcomm® QCS8750 | 1.255 ms | 0 - 25 MB | NPU
| QuickSRNetLarge | ONNX | float | Qualcomm® QCS7181 | 2.046 ms | 180 - 180 MB | NPU
| QuickSRNetLarge | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.336 ms | 0 - 28 MB | NPU
| QuickSRNetLarge | ONNX | w8a8 | Snapdragon® X2 Elite | 0.375 ms | 212 - 212 MB | NPU
| QuickSRNetLarge | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.482 ms | 0 - 36 MB | NPU
| QuickSRNetLarge | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.736 ms | 0 - 15 MB | NPU
| QuickSRNetLarge | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.384 ms | 0 - 28 MB | NPU
| QuickSRNetLarge | ONNX | w8a8 | Qualcomm® QCS9075 | 0.942 ms | 0 - 46 MB | NPU
| QuickSRNetLarge | ONNX | w8a8 | Qualcomm® QCS8750 | 0.384 ms | 0 - 28 MB | NPU
| QuickSRNetLarge | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.843 ms | 0 - 26 MB | NPU
| QuickSRNetLarge | QNN_DLC | float | Snapdragon® X2 Elite | 1.226 ms | 0 - 0 MB | NPU
| QuickSRNetLarge | QNN_DLC | float | Snapdragon® X Elite | 1.953 ms | 0 - 0 MB | NPU
| QuickSRNetLarge | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.285 ms | 0 - 36 MB | NPU
| QuickSRNetLarge | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 1.799 ms | 0 - 2 MB | NPU
| QuickSRNetLarge | QNN_DLC | float | Qualcomm® SA8775P | 3.385 ms | 0 - 24 MB | NPU
| QuickSRNetLarge | QNN_DLC | float | Qualcomm® SA8650P | 3.385 ms | 0 - 24 MB | NPU
| QuickSRNetLarge | QNN_DLC | float | Qualcomm® SA8255P | 3.385 ms | 0 - 24 MB | NPU
| QuickSRNetLarge | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 3.265 ms | 0 - 39 MB | NPU
| QuickSRNetLarge | QNN_DLC | float | Qualcomm® SA8295P | 3.945 ms | 0 - 20 MB | NPU
| QuickSRNetLarge | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.038 ms | 0 - 23 MB | NPU
| QuickSRNetLarge | QNN_DLC | float | Qualcomm® QCS9075 | 3.357 ms | 0 - 5 MB | NPU
| QuickSRNetLarge | QNN_DLC | float | Qualcomm® QCS8750 | 1.038 ms | 0 - 23 MB | NPU
| QuickSRNetLarge | QNN_DLC | float | Qualcomm® QCS7181 | 1.953 ms | 0 - 0 MB | NPU
| QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.26 ms | 0 - 27 MB | NPU
| QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.402 ms | 0 - 0 MB | NPU
| QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.766 ms | 0 - 0 MB | NPU
| QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.44 ms | 0 - 34 MB | NPU
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 2.721 ms | 2 - 4 MB | NPU
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS8275 | 2.087 ms | 0 - 25 MB | NPU
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.642 ms | 0 - 1 MB | NPU
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.847 ms | 0 - 26 MB | NPU
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® SA8650P | 0.847 ms | 0 - 26 MB | NPU
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® SA8255P | 0.847 ms | 0 - 26 MB | NPU
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® SA7255P | 2.087 ms | 0 - 25 MB | NPU
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.388 ms | 0 - 21 MB | NPU
| QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.909 ms | 0 - 22 MB | NPU
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 8.33 ms | 0 - 135 MB | NPU
| QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.369 ms | 0 - 29 MB | NPU
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 0.845 ms | 2 - 4 MB | NPU
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.832 ms | 0 - 35 MB | NPU
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS7790 | 0.909 ms | 0 - 22 MB | NPU
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS8750 | 0.369 ms | 0 - 29 MB | NPU
| QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS7181 | 0.766 ms | 0 - 0 MB | NPU
| QuickSRNetLarge | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.863 ms | 0 - 28 MB | NPU
| QuickSRNetLarge | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.45 ms | 0 - 39 MB | NPU
| QuickSRNetLarge | TFLITE | float | Qualcomm® QCS8275 | 12.179 ms | 3 - 27 MB | NPU
| QuickSRNetLarge | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 2.141 ms | 0 - 2 MB | NPU
| QuickSRNetLarge | TFLITE | float | Qualcomm® SA8775P | 3.803 ms | 0 - 26 MB | NPU
| QuickSRNetLarge | TFLITE | float | Qualcomm® SA8650P | 3.803 ms | 0 - 26 MB | NPU
| QuickSRNetLarge | TFLITE | float | Qualcomm® SA8255P | 3.803 ms | 0 - 26 MB | NPU
| QuickSRNetLarge | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 3.49 ms | 0 - 39 MB | NPU
| QuickSRNetLarge | TFLITE | float | Qualcomm® SA8295P | 4.204 ms | 0 - 22 MB | NPU
| QuickSRNetLarge | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.087 ms | 0 - 25 MB | NPU
| QuickSRNetLarge | TFLITE | float | Qualcomm® QCS9075 | 3.702 ms | 3 - 9 MB | NPU
| QuickSRNetLarge | TFLITE | float | Qualcomm® SA7255P | 12.179 ms | 3 - 27 MB | NPU
| QuickSRNetLarge | TFLITE | float | Qualcomm® QCS8750 | 1.087 ms | 0 - 25 MB | NPU
| QuickSRNetLarge | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.287 ms | 0 - 28 MB | NPU
| QuickSRNetLarge | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.494 ms | 0 - 34 MB | NPU
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCS6490 | 2.94 ms | 1 - 4 MB | NPU
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCS8275 | 2.191 ms | 0 - 25 MB | NPU
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.778 ms | 0 - 2 MB | NPU
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® SA8775P | 0.998 ms | 0 - 27 MB | NPU
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® SA8650P | 0.998 ms | 0 - 27 MB | NPU
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® SA8255P | 0.998 ms | 0 - 27 MB | NPU
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® SA7255P | 2.191 ms | 0 - 25 MB | NPU
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® SA8295P | 1.468 ms | 0 - 24 MB | NPU
| QuickSRNetLarge | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.974 ms | 0 - 24 MB | NPU
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCM6690 | 8.555 ms | 2 - 139 MB | NPU
| QuickSRNetLarge | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.388 ms | 0 - 24 MB | NPU
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCS9075 | 0.97 ms | 0 - 3 MB | NPU
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.917 ms | 0 - 36 MB | NPU
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCS7790 | 0.974 ms | 0 - 24 MB | NPU
| QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCS8750 | 0.388 ms | 0 - 24 MB | NPU

## License
* The license for the original implementation of QuickSRNetLarge can be found
  [here](https://github.com/quic/aimet-model-zoo/blob/develop/LICENSE.md).

## References
* [QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms](https://arxiv.org/abs/2303.04336)
* [Source Model Implementation](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/quicksrnet)

## Community
* Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
* For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).