---
library_name: pytorch
license: other
tags:
- bu_auto
- android
pipeline_tag: image-classification

---

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

# 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](https://github.com/pytorch/vision/blob/main/torchvision/models/convnext.py).
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/convnext_tiny) 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 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_tiny/releases/v0.47.0/convnext_tiny-onnx-float.zip)
| ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_tiny/releases/v0.47.0/convnext_tiny-onnx-w8a16.zip)
| QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_tiny/releases/v0.47.0/convnext_tiny-qnn_dlc-float.zip)
| QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_tiny/releases/v0.47.0/convnext_tiny-qnn_dlc-w8a16.zip)
| TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_tiny/releases/v0.47.0/convnext_tiny-tflite-float.zip)

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


### 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/convnext_tiny) 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](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/convnext_tiny) for usage instructions.

## Model Details

**Model Type:** Model_use_case.image_classification

**Model Stats:**
- Model checkpoint: Imagenet
- Input resolution: 224x224
- Number of parameters: 28.6M
- Model size (float): 109 MB
- Model size (w8a16): 28.9 MB

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| ConvNext-Tiny | ONNX | float | Snapdragon® X Elite | 2.891 ms | 56 - 56 MB | NPU
| ConvNext-Tiny | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.035 ms | 0 - 170 MB | NPU
| ConvNext-Tiny | ONNX | float | Qualcomm® QCS8550 (Proxy) | 2.735 ms | 1 - 3 MB | NPU
| ConvNext-Tiny | ONNX | float | Qualcomm® QCS9075 | 3.941 ms | 1 - 4 MB | NPU
| ConvNext-Tiny | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.551 ms | 0 - 128 MB | NPU
| ConvNext-Tiny | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.274 ms | 0 - 126 MB | NPU
| ConvNext-Tiny | ONNX | float | Snapdragon® X2 Elite | 1.338 ms | 57 - 57 MB | NPU
| ConvNext-Tiny | ONNX | w8a16 | Snapdragon® X Elite | 2.821 ms | 29 - 29 MB | NPU
| ConvNext-Tiny | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.826 ms | 0 - 141 MB | NPU
| ConvNext-Tiny | ONNX | w8a16 | Qualcomm® QCS6490 | 373.805 ms | 49 - 63 MB | CPU
| ConvNext-Tiny | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 2.541 ms | 0 - 35 MB | NPU
| ConvNext-Tiny | ONNX | w8a16 | Qualcomm® QCS9075 | 2.665 ms | 0 - 3 MB | NPU
| ConvNext-Tiny | ONNX | w8a16 | Qualcomm® QCM6690 | 210.517 ms | 59 - 72 MB | CPU
| ConvNext-Tiny | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 1.376 ms | 0 - 109 MB | NPU
| ConvNext-Tiny | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 202.572 ms | 57 - 71 MB | CPU
| ConvNext-Tiny | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.101 ms | 0 - 115 MB | NPU
| ConvNext-Tiny | ONNX | w8a16 | Snapdragon® X2 Elite | 1.198 ms | 29 - 29 MB | NPU
| ConvNext-Tiny | QNN_DLC | float | Snapdragon® X Elite | 3.931 ms | 1 - 1 MB | NPU
| ConvNext-Tiny | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.659 ms | 0 - 170 MB | NPU
| ConvNext-Tiny | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 15.263 ms | 1 - 124 MB | NPU
| ConvNext-Tiny | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 3.678 ms | 1 - 2 MB | NPU
| ConvNext-Tiny | QNN_DLC | float | Qualcomm® SA8775P | 5.035 ms | 1 - 125 MB | NPU
| ConvNext-Tiny | QNN_DLC | float | Qualcomm® QCS9075 | 4.875 ms | 1 - 3 MB | NPU
| ConvNext-Tiny | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 9.713 ms | 0 - 170 MB | NPU
| ConvNext-Tiny | QNN_DLC | float | Qualcomm® SA7255P | 15.263 ms | 1 - 124 MB | NPU
| ConvNext-Tiny | QNN_DLC | float | Qualcomm® SA8295P | 8.956 ms | 1 - 125 MB | NPU
| ConvNext-Tiny | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.028 ms | 0 - 126 MB | NPU
| ConvNext-Tiny | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.631 ms | 1 - 127 MB | NPU
| ConvNext-Tiny | QNN_DLC | float | Snapdragon® X2 Elite | 2.533 ms | 1 - 1 MB | NPU
| ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® X Elite | 3.407 ms | 0 - 0 MB | NPU
| ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 2.198 ms | 0 - 122 MB | NPU
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 9.043 ms | 0 - 2 MB | NPU
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 6.814 ms | 0 - 97 MB | NPU
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 3.123 ms | 0 - 2 MB | NPU
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® SA8775P | 3.499 ms | 0 - 98 MB | NPU
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 3.347 ms | 0 - 2 MB | NPU
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 23.111 ms | 0 - 250 MB | NPU
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 4.192 ms | 0 - 123 MB | NPU
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® SA7255P | 6.814 ms | 0 - 97 MB | NPU
| ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® SA8295P | 4.732 ms | 0 - 97 MB | NPU
| ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 1.605 ms | 0 - 98 MB | NPU
| ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 3.426 ms | 0 - 108 MB | NPU
| ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.283 ms | 0 - 100 MB | NPU
| ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 1.623 ms | 0 - 0 MB | NPU
| ConvNext-Tiny | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.116 ms | 0 - 168 MB | NPU
| ConvNext-Tiny | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 13.987 ms | 0 - 121 MB | NPU
| ConvNext-Tiny | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 2.836 ms | 0 - 3 MB | NPU
| ConvNext-Tiny | TFLITE | float | Qualcomm® SA8775P | 4.288 ms | 0 - 122 MB | NPU
| ConvNext-Tiny | TFLITE | float | Qualcomm® QCS9075 | 4.077 ms | 0 - 59 MB | NPU
| ConvNext-Tiny | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 8.899 ms | 0 - 164 MB | NPU
| ConvNext-Tiny | TFLITE | float | Qualcomm® SA7255P | 13.987 ms | 0 - 121 MB | NPU
| ConvNext-Tiny | TFLITE | float | Qualcomm® SA8295P | 7.899 ms | 0 - 118 MB | NPU
| ConvNext-Tiny | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.591 ms | 0 - 126 MB | NPU
| ConvNext-Tiny | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.304 ms | 0 - 123 MB | NPU

## License
* The license for the original implementation of ConvNext-Tiny can be found
  [here](https://github.com/pytorch/vision/blob/main/LICENSE).

## References
* [A ConvNet for the 2020s](https://arxiv.org/abs/2201.03545)
* [Source Model Implementation](https://github.com/pytorch/vision/blob/main/torchvision/models/convnext.py)

## 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).