---
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/quicksrnetsmall/web-assets/model_demo.png)

# QuickSRNetSmall: Optimized for Qualcomm Devices

QuickSRNet Small is designed for upscaling images on mobile platforms to sharpen in real-time.

This is based on the implementation of QuickSRNetSmall 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/quic/ai-hub-models/blob/main/qai_hub_models/models/quicksrnetsmall) 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 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/quicksrnetsmall/releases/v0.46.0/quicksrnetsmall-onnx-float.zip)
| QNN_DLC | float | Universal | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/quicksrnetsmall/releases/v0.46.0/quicksrnetsmall-qnn_dlc-float.zip)
| QNN_DLC | w8a8 | Universal | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/quicksrnetsmall/releases/v0.46.0/quicksrnetsmall-qnn_dlc-w8a8.zip)
| TFLITE | float | Universal | QAIRT 2.42, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/quicksrnetsmall/releases/v0.46.0/quicksrnetsmall-tflite-float.zip)
| TFLITE | w8a8 | Universal | QAIRT 2.42, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/quicksrnetsmall/releases/v0.46.0/quicksrnetsmall-tflite-w8a8.zip)

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


### Option 2: Export with Custom Configurations

Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/quicksrnetsmall) 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 [QuickSRNetSmall on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/quicksrnetsmall) for usage instructions.

## Model Details

**Model Type:** Model_use_case.super_resolution

**Model Stats:**
- Model checkpoint: quicksrnet_small_3x_checkpoint
- Input resolution: 128x128
- Number of parameters: 33.3K
- Model size (float): 133 KB
- Model size (w8a8): 41.7 KB

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| QuickSRNetSmall | ONNX | float | Snapdragon® X Elite | 1.049 ms | 8 - 8 MB | NPU
| QuickSRNetSmall | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.809 ms | 0 - 97 MB | NPU
| QuickSRNetSmall | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1.138 ms | 0 - 44 MB | NPU
| QuickSRNetSmall | ONNX | float | Qualcomm® QCS9075 | 1.436 ms | 6 - 9 MB | NPU
| QuickSRNetSmall | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.594 ms | 0 - 91 MB | NPU
| QuickSRNetSmall | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.512 ms | 0 - 89 MB | NPU
| QuickSRNetSmall | QNN_DLC | float | Snapdragon® X Elite | 0.842 ms | 0 - 0 MB | NPU
| QuickSRNetSmall | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.452 ms | 0 - 28 MB | NPU
| QuickSRNetSmall | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 1.85 ms | 0 - 21 MB | NPU
| QuickSRNetSmall | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 0.742 ms | 0 - 1 MB | NPU
| QuickSRNetSmall | QNN_DLC | float | Qualcomm® SA8775P | 1.082 ms | 0 - 22 MB | NPU
| QuickSRNetSmall | QNN_DLC | float | Qualcomm® QCS9075 | 1.102 ms | 0 - 5 MB | NPU
| QuickSRNetSmall | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 1.04 ms | 0 - 29 MB | NPU
| QuickSRNetSmall | QNN_DLC | float | Qualcomm® SA7255P | 1.85 ms | 0 - 21 MB | NPU
| QuickSRNetSmall | QNN_DLC | float | Qualcomm® SA8295P | 1.383 ms | 0 - 17 MB | NPU
| QuickSRNetSmall | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.359 ms | 0 - 24 MB | NPU
| QuickSRNetSmall | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.326 ms | 0 - 24 MB | NPU
| QuickSRNetSmall | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.426 ms | 0 - 0 MB | NPU
| QuickSRNetSmall | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.214 ms | 0 - 24 MB | NPU
| QuickSRNetSmall | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 1.279 ms | 0 - 2 MB | NPU
| QuickSRNetSmall | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 0.774 ms | 0 - 19 MB | NPU
| QuickSRNetSmall | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.319 ms | 0 - 1 MB | NPU
| QuickSRNetSmall | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.516 ms | 0 - 19 MB | NPU
| QuickSRNetSmall | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 0.497 ms | 0 - 2 MB | NPU
| QuickSRNetSmall | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 1.208 ms | 0 - 16 MB | NPU
| QuickSRNetSmall | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.463 ms | 0 - 25 MB | NPU
| QuickSRNetSmall | QNN_DLC | w8a8 | Qualcomm® SA7255P | 0.774 ms | 0 - 19 MB | NPU
| QuickSRNetSmall | QNN_DLC | w8a8 | Qualcomm® SA8295P | 0.703 ms | 0 - 15 MB | NPU
| QuickSRNetSmall | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.174 ms | 0 - 21 MB | NPU
| QuickSRNetSmall | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.351 ms | 0 - 16 MB | NPU
| QuickSRNetSmall | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.145 ms | 0 - 20 MB | NPU
| QuickSRNetSmall | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.628 ms | 0 - 28 MB | NPU
| QuickSRNetSmall | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 2.389 ms | 0 - 21 MB | NPU
| QuickSRNetSmall | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 1.003 ms | 0 - 1 MB | NPU
| QuickSRNetSmall | TFLITE | float | Qualcomm® SA8775P | 1.419 ms | 0 - 21 MB | NPU
| QuickSRNetSmall | TFLITE | float | Qualcomm® QCS9075 | 1.27 ms | 3 - 8 MB | NPU
| QuickSRNetSmall | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 1.318 ms | 1 - 30 MB | NPU
| QuickSRNetSmall | TFLITE | float | Qualcomm® SA7255P | 2.389 ms | 0 - 21 MB | NPU
| QuickSRNetSmall | TFLITE | float | Qualcomm® SA8295P | 1.652 ms | 0 - 17 MB | NPU
| QuickSRNetSmall | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.46 ms | 0 - 20 MB | NPU
| QuickSRNetSmall | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.397 ms | 0 - 23 MB | NPU
| QuickSRNetSmall | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.27 ms | 0 - 25 MB | NPU
| QuickSRNetSmall | TFLITE | w8a8 | Qualcomm® QCS6490 | 1.042 ms | 0 - 2 MB | NPU
| QuickSRNetSmall | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 0.89 ms | 0 - 19 MB | NPU
| QuickSRNetSmall | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.398 ms | 0 - 1 MB | NPU
| QuickSRNetSmall | TFLITE | w8a8 | Qualcomm® SA8775P | 0.594 ms | 0 - 20 MB | NPU
| QuickSRNetSmall | TFLITE | w8a8 | Qualcomm® QCS9075 | 0.521 ms | 0 - 3 MB | NPU
| QuickSRNetSmall | TFLITE | w8a8 | Qualcomm® QCM6690 | 1.5 ms | 0 - 16 MB | NPU
| QuickSRNetSmall | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.466 ms | 0 - 26 MB | NPU
| QuickSRNetSmall | TFLITE | w8a8 | Qualcomm® SA7255P | 0.89 ms | 0 - 19 MB | NPU
| QuickSRNetSmall | TFLITE | w8a8 | Qualcomm® SA8295P | 0.806 ms | 0 - 15 MB | NPU
| QuickSRNetSmall | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.197 ms | 0 - 21 MB | NPU
| QuickSRNetSmall | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.415 ms | 0 - 17 MB | NPU
| QuickSRNetSmall | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.162 ms | 0 - 20 MB | NPU

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

## 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).