---
title: RegNet-Y-800MF
canonical_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/RegNet-Y-800MF"
md_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/RegNet-Y-800MF.md"
repository: Qualcomm-AI-Hub/RegNet-Y-800MF
last_updated: 2026-10-16
license: bsd-3-clause
pipeline_tag: image-classification
tasks:
  - image-classification
downloads: 0
stars: 0
tags:
  - android
---

# RegNet-Y-800MF

> RegNet-Y-800MF - Qualcomm-AI-Hub 在 ModelScope 开源的模型。RegNet-Y-800MF: Optimized for Qualcomm Devices

Qualcomm-AI-Hub/RegNet-Y-800MF 是 ModelScope 魔搭社区上的image-classification模型，采用 bsd-3-clause 许可。

- **Repository**: Qualcomm-AI-Hub/RegNet-Y-800MF
- **License**: bsd-3-clause
- **Tasks**: image-classification
- **Tags**: android
- **Downloads**: 0
- **Stars**: 0
- **Last updated**: 2026-10-16

Source: https://www.modelscope.cn/models/Qualcomm-AI-Hub/RegNet-Y-800MF

---

![](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/regnet_y_800mf/web-assets/model_demo.png)

# RegNet-Y-800MF: Optimized for Qualcomm Devices

RegNet_Y_800MF is part of the RegNet family of models designed for efficient and scalable image classification. It uses a simple yet effective design space to balance performance and computational cost, making it suitable for mobile and edge devices.

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/regnet_y_800mf) 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/regnet_y_800mf/releases/v0.62.1/regnet_y_800mf-onnx-float.zip)
| ONNX | w8a8 | 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/regnet_y_800mf/releases/v0.62.1/regnet_y_800mf-onnx-w8a8.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/regnet_y_800mf/releases/v0.62.1/regnet_y_800mf-qnn_dlc-float.zip)
| QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/regnet_y_800mf/releases/v0.62.1/regnet_y_800mf-qnn_dlc-w8a8.zip)
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/regnet_y_800mf/releases/v0.62.1/regnet_y_800mf-tflite-float.zip)
| TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/regnet_y_800mf/releases/v0.62.1/regnet_y_800mf-tflite-w8a8.zip)

For more device-specific assets and performance metrics, visit **[RegNet-Y-800MF on Qualcomm® AI Hub](https://aihub.qualcomm.cn/models/regnet_y_800mf)**.


### 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/regnet_y_800mf) 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 [RegNet-Y-800MF on GitHub](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/regnet_y_800mf) for usage instructions.

## Model Details

**Model Type:** Model_use_case.image_classification

**Model Stats:**
- Input resolution: 1x3x224
- Model checkpoint: regnet_y_800mf-1b27b58c.pth
- Model size: ~6.3 MB

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| RegNet-Y-800MF | ONNX | float | Snapdragon® X2 Elite | 0.538 ms | 2 - 2 MB | NPU
| RegNet-Y-800MF | ONNX | float | Snapdragon® X Elite | 1.136 ms | 15 - 15 MB | NPU
| RegNet-Y-800MF | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.716 ms | 0 - 80 MB | NPU
| RegNet-Y-800MF | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 1.458 ms | 1 - 74 MB | NPU
| RegNet-Y-800MF | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 1.311 ms | 0 - 4 MB | NPU
| RegNet-Y-800MF | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.09 ms | 0 - 17 MB | NPU
| RegNet-Y-800MF | ONNX | float | Qualcomm® QCS8450 | 1.458 ms | 1 - 74 MB | NPU
| RegNet-Y-800MF | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 1.404 ms | 1 - 3 MB | NPU
| RegNet-Y-800MF | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.136 ms | 15 - 15 MB | NPU
| RegNet-Y-800MF | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 0.559 ms | 0 - 55 MB | NPU
| RegNet-Y-800MF | ONNX | float | Snapdragon® 8 Elite Mobile | 0.559 ms | 0 - 55 MB | NPU
| RegNet-Y-800MF | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.537 ms | 0 - 56 MB | NPU
| RegNet-Y-800MF | ONNX | w8a8 | Snapdragon® X2 Elite | 0.373 ms | 1 - 1 MB | NPU
| RegNet-Y-800MF | ONNX | w8a8 | Snapdragon® X Elite | 0.719 ms | 8 - 8 MB | NPU
| RegNet-Y-800MF | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.494 ms | 0 - 85 MB | NPU
| RegNet-Y-800MF | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.871 ms | 0 - 83 MB | NPU
| RegNet-Y-800MF | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 1.633 ms | 0 - 3 MB | NPU
| RegNet-Y-800MF | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 0.776 ms | 0 - 4 MB | NPU
| RegNet-Y-800MF | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.707 ms | 0 - 84 MB | NPU
| RegNet-Y-800MF | ONNX | w8a8 | Qualcomm® QCS8450 | 0.871 ms | 0 - 83 MB | NPU
| RegNet-Y-800MF | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.831 ms | 0 - 3 MB | NPU
| RegNet-Y-800MF | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.719 ms | 8 - 8 MB | NPU
| RegNet-Y-800MF | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 2.567 ms | 0 - 62 MB | NPU
| RegNet-Y-800MF | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.688 ms | 0 - 56 MB | NPU
| RegNet-Y-800MF | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.432 ms | 0 - 60 MB | NPU
| RegNet-Y-800MF | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 0.432 ms | 0 - 60 MB | NPU
| RegNet-Y-800MF | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.377 ms | 0 - 61 MB | NPU
| RegNet-Y-800MF | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.688 ms | 0 - 56 MB | NPU
| RegNet-Y-800MF | QNN_DLC | float | Snapdragon® X2 Elite | 0.81 ms | 1 - 1 MB | NPU
| RegNet-Y-800MF | QNN_DLC | float | Snapdragon® X Elite | 1.618 ms | 1 - 1 MB | NPU
| RegNet-Y-800MF | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.92 ms | 0 - 76 MB | NPU
| RegNet-Y-800MF | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 2.229 ms | 0 - 72 MB | NPU
| RegNet-Y-800MF | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 1.554 ms | 1 - 4 MB | NPU
| RegNet-Y-800MF | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.397 ms | 1 - 2 MB | NPU
| RegNet-Y-800MF | QNN_DLC | float | Qualcomm® SA8775P | 1.881 ms | 1 - 52 MB | NPU
| RegNet-Y-800MF | QNN_DLC | float | Qualcomm® SA8650P | 1.881 ms | 1 - 52 MB | NPU
| RegNet-Y-800MF | QNN_DLC | float | Qualcomm® SA8255P | 1.881 ms | 1 - 52 MB | NPU
| RegNet-Y-800MF | QNN_DLC | float | Qualcomm® QCS8450 | 2.229 ms | 0 - 72 MB | NPU
| RegNet-Y-800MF | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 1.699 ms | 1 - 3 MB | NPU
| RegNet-Y-800MF | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.618 ms | 1 - 1 MB | NPU
| RegNet-Y-800MF | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 0.694 ms | 1 - 55 MB | NPU
| RegNet-Y-800MF | QNN_DLC | float | Qualcomm® SA7255P | 4.049 ms | 0 - 49 MB | NPU
| RegNet-Y-800MF | QNN_DLC | float | Qualcomm® SA8295P | 2.14 ms | 0 - 45 MB | NPU
| RegNet-Y-800MF | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 0.694 ms | 1 - 55 MB | NPU
| RegNet-Y-800MF | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.619 ms | 1 - 56 MB | NPU
| RegNet-Y-800MF | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.452 ms | 0 - 0 MB | NPU
| RegNet-Y-800MF | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.832 ms | 0 - 0 MB | NPU
| RegNet-Y-800MF | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.494 ms | 0 - 66 MB | NPU
| RegNet-Y-800MF | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.853 ms | 0 - 70 MB | NPU
| RegNet-Y-800MF | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 1.945 ms | 2 - 4 MB | NPU
| RegNet-Y-800MF | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 0.736 ms | 0 - 3 MB | NPU
| RegNet-Y-800MF | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.707 ms | 0 - 16 MB | NPU
| RegNet-Y-800MF | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.919 ms | 0 - 50 MB | NPU
| RegNet-Y-800MF | QNN_DLC | w8a8 | Qualcomm® SA8650P | 0.919 ms | 0 - 50 MB | NPU
| RegNet-Y-800MF | QNN_DLC | w8a8 | Qualcomm® SA8255P | 0.919 ms | 0 - 50 MB | NPU
| RegNet-Y-800MF | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 0.853 ms | 0 - 70 MB | NPU
| RegNet-Y-800MF | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.783 ms | 0 - 2 MB | NPU
| RegNet-Y-800MF | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.832 ms | 0 - 0 MB | NPU
| RegNet-Y-800MF | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 2.875 ms | 0 - 48 MB | NPU
| RegNet-Y-800MF | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.718 ms | 0 - 46 MB | NPU
| RegNet-Y-800MF | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.382 ms | 0 - 51 MB | NPU
| RegNet-Y-800MF | QNN_DLC | w8a8 | Qualcomm® SA7255P | 1.582 ms | 0 - 48 MB | NPU
| RegNet-Y-800MF | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.104 ms | 0 - 46 MB | NPU
| RegNet-Y-800MF | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.382 ms | 0 - 51 MB | NPU
| RegNet-Y-800MF | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.309 ms | 0 - 48 MB | NPU
| RegNet-Y-800MF | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.718 ms | 0 - 46 MB | NPU
| RegNet-Y-800MF | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.912 ms | 0 - 87 MB | NPU
| RegNet-Y-800MF | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 2.199 ms | 0 - 77 MB | NPU
| RegNet-Y-800MF | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 1.556 ms | 0 - 18 MB | NPU
| RegNet-Y-800MF | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.419 ms | 0 - 2 MB | NPU
| RegNet-Y-800MF | TFLITE | float | Qualcomm® SA8775P | 1.902 ms | 0 - 62 MB | NPU
| RegNet-Y-800MF | TFLITE | float | Qualcomm® SA8650P | 1.902 ms | 0 - 62 MB | NPU
| RegNet-Y-800MF | TFLITE | float | Qualcomm® SA8255P | 1.902 ms | 0 - 62 MB | NPU
| RegNet-Y-800MF | TFLITE | float | Qualcomm® QCS8450 | 2.199 ms | 0 - 77 MB | NPU
| RegNet-Y-800MF | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1.709 ms | 0 - 17 MB | NPU
| RegNet-Y-800MF | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 0.684 ms | 0 - 55 MB | NPU
| RegNet-Y-800MF | TFLITE | float | Qualcomm® SA7255P | 4.029 ms | 0 - 59 MB | NPU
| RegNet-Y-800MF | TFLITE | float | Qualcomm® SA8295P | 2.153 ms | 0 - 50 MB | NPU
| RegNet-Y-800MF | TFLITE | float | Snapdragon® 8 Elite Mobile | 0.684 ms | 0 - 55 MB | NPU
| RegNet-Y-800MF | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.617 ms | 0 - 57 MB | NPU
| RegNet-Y-800MF | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.359 ms | 0 - 68 MB | NPU
| RegNet-Y-800MF | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.67 ms | 0 - 73 MB | NPU
| RegNet-Y-800MF | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 1.486 ms | 0 - 9 MB | NPU
| RegNet-Y-800MF | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 0.582 ms | 0 - 10 MB | NPU
| RegNet-Y-800MF | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.502 ms | 0 - 2 MB | NPU
| RegNet-Y-800MF | TFLITE | w8a8 | Qualcomm® SA8775P | 0.742 ms | 0 - 51 MB | NPU
| RegNet-Y-800MF | TFLITE | w8a8 | Qualcomm® SA8650P | 0.742 ms | 0 - 51 MB | NPU
| RegNet-Y-800MF | TFLITE | w8a8 | Qualcomm® SA8255P | 0.742 ms | 0 - 51 MB | NPU
| RegNet-Y-800MF | TFLITE | w8a8 | Qualcomm® QCS8450 | 0.67 ms | 0 - 73 MB | NPU
| RegNet-Y-800MF | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.608 ms | 0 - 9 MB | NPU
| RegNet-Y-800MF | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 2.33 ms | 0 - 44 MB | NPU
| RegNet-Y-800MF | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.537 ms | 0 - 42 MB | NPU
| RegNet-Y-800MF | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.302 ms | 0 - 43 MB | NPU
| RegNet-Y-800MF | TFLITE | w8a8 | Qualcomm® SA7255P | 1.33 ms | 0 - 47 MB | NPU
| RegNet-Y-800MF | TFLITE | w8a8 | Qualcomm® SA8295P | 0.91 ms | 0 - 44 MB | NPU
| RegNet-Y-800MF | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 0.302 ms | 0 - 43 MB | NPU
| RegNet-Y-800MF | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.255 ms | 0 - 44 MB | NPU
| RegNet-Y-800MF | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.537 ms | 0 - 42 MB | NPU

## License
* The license for the original implementation of RegNet-Y-800MF can be found
  [here](https://github.com/pytorch/vision/blob/main/LICENSE).



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