---
title: CavaFace
canonical_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/CavaFace"
md_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/CavaFace.md"
repository: Qualcomm-AI-Hub/CavaFace
last_updated: 2026-10-16
license: mit
downloads: 0
stars: 0
tags:
  - real_time
  - bu_auto
  - android
---

# CavaFace

> CavaFace - Qualcomm-AI-Hub 在 ModelScope 开源的模型。CavaFace: Optimized for Qualcomm Devices

Qualcomm-AI-Hub/CavaFace 是 ModelScope 魔搭社区上的机器学习模型，采用 mit 许可。

- **Repository**: Qualcomm-AI-Hub/CavaFace
- **License**: mit
- **Tags**: real_time, bu_auto, android
- **Downloads**: 0
- **Stars**: 0
- **Last updated**: 2026-10-16

Source: https://www.modelscope.cn/models/Qualcomm-AI-Hub/CavaFace

---

![](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/cavaface/web-assets/model_demo.png)

# CavaFace: Optimized for Qualcomm Devices

A PyTorch-based framework for training face recognition models that generates facial embeddings for verification and identification tasks

This is based on the implementation of CavaFace found [here](https://github.com/cavalleria/cavaface).
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-cn/blob/main/src/qai_hub_models/models/cavaface) 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.cn) 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 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/cavaface/releases/v0.62.1/cavaface-onnx-float.zip)
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/cavaface/releases/v0.62.1/cavaface-qnn_dlc-float.zip)
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/cavaface/releases/v0.62.1/cavaface-tflite-float.zip)

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


### Option 2: Export with Custom Configurations

Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/cavaface) 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 [CavaFace on GitHub](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/cavaface) for usage instructions.

## Model Details

**Model Type:** Model_use_case.object_detection

**Model Stats:**
- Input resolution: 112x112
- Model checkpoint: IR_SE_100_Combined_Epoch_24.pt
- Model size (float): 249.96MB
- Number of parameters: 65.5M

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| CavaFace | ONNX | float | Snapdragon® X2 Elite | 2.329 ms | 1 - 1 MB | NPU
| CavaFace | ONNX | float | Snapdragon® X Elite | 4.304 ms | 127 - 127 MB | NPU
| CavaFace | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 3.198 ms | 0 - 137 MB | NPU
| CavaFace | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 9.539 ms | 0 - 229 MB | NPU
| CavaFace | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 7.641 ms | 0 - 4 MB | NPU
| CavaFace | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.314 ms | 0 - 130 MB | NPU
| CavaFace | ONNX | float | Qualcomm® QCS8450 | 9.539 ms | 0 - 229 MB | NPU
| CavaFace | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 6.751 ms | 0 - 3 MB | NPU
| CavaFace | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 4.304 ms | 127 - 127 MB | NPU
| CavaFace | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 2.627 ms | 0 - 89 MB | NPU
| CavaFace | ONNX | float | Snapdragon® 8 Elite Mobile | 2.627 ms | 0 - 89 MB | NPU
| CavaFace | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.284 ms | 0 - 92 MB | NPU
| CavaFace | QNN_DLC | float | Snapdragon® X2 Elite | 2.563 ms | 0 - 0 MB | NPU
| CavaFace | QNN_DLC | float | Snapdragon® X Elite | 4.454 ms | 0 - 0 MB | NPU
| CavaFace | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.197 ms | 0 - 129 MB | NPU
| CavaFace | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 9.589 ms | 0 - 220 MB | NPU
| CavaFace | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 7.598 ms | 0 - 3 MB | NPU
| CavaFace | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.287 ms | 0 - 2 MB | NPU
| CavaFace | QNN_DLC | float | Qualcomm® SA8775P | 6.932 ms | 0 - 82 MB | NPU
| CavaFace | QNN_DLC | float | Qualcomm® SA8650P | 6.932 ms | 0 - 82 MB | NPU
| CavaFace | QNN_DLC | float | Qualcomm® SA8255P | 6.932 ms | 0 - 82 MB | NPU
| CavaFace | QNN_DLC | float | Qualcomm® QCS8450 | 9.589 ms | 0 - 220 MB | NPU
| CavaFace | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 6.679 ms | 0 - 2 MB | NPU
| CavaFace | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 4.454 ms | 0 - 0 MB | NPU
| CavaFace | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 2.61 ms | 0 - 84 MB | NPU
| CavaFace | QNN_DLC | float | Qualcomm® SA7255P | 24.705 ms | 0 - 80 MB | NPU
| CavaFace | QNN_DLC | float | Qualcomm® SA8295P | 8.03 ms | 0 - 199 MB | NPU
| CavaFace | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 2.61 ms | 0 - 84 MB | NPU
| CavaFace | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.255 ms | 0 - 82 MB | NPU
| CavaFace | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3.151 ms | 0 - 245 MB | NPU
| CavaFace | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 9.45 ms | 0 - 331 MB | NPU
| CavaFace | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 7.526 ms | 0 - 129 MB | NPU
| CavaFace | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.168 ms | 0 - 2 MB | NPU
| CavaFace | TFLITE | float | Qualcomm® SA8775P | 6.893 ms | 0 - 96 MB | NPU
| CavaFace | TFLITE | float | Qualcomm® SA8650P | 6.893 ms | 0 - 96 MB | NPU
| CavaFace | TFLITE | float | Qualcomm® SA8255P | 6.893 ms | 0 - 96 MB | NPU
| CavaFace | TFLITE | float | Qualcomm® QCS8450 | 9.45 ms | 0 - 331 MB | NPU
| CavaFace | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 6.605 ms | 0 - 128 MB | NPU
| CavaFace | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 2.587 ms | 0 - 98 MB | NPU
| CavaFace | TFLITE | float | Qualcomm® SA7255P | 24.513 ms | 0 - 95 MB | NPU
| CavaFace | TFLITE | float | Qualcomm® SA8295P | 7.976 ms | 0 - 209 MB | NPU
| CavaFace | TFLITE | float | Snapdragon® 8 Elite Mobile | 2.587 ms | 0 - 98 MB | NPU
| CavaFace | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.235 ms | 0 - 98 MB | NPU

## License
* The license for the original implementation of CavaFace can be found
  [here](https://github.com/cavalleria/cavaface/blob/master/LICENSE).

## References
* [Source Model Implementation](https://github.com/cavalleria/cavaface)

## Community
* For questions or feedback, chat with our engineers in [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.cn).