---
title: ai_model_hub_25_Q3
canonical_url: "https://www.modelscope.cn/models/cix/ai_model_hub_25_Q3"
md_url: "https://www.modelscope.cn/models/cix/ai_model_hub_25_Q3.md"
repository: cix/ai_model_hub_25_Q3
chinese_name: ai_model_hub_25_Q3
last_updated: 2025-10-10
parameters: 1.2B
tensor_type:
  - I64
  - F32
library_name:
  - onnx
  - safetensors
  - tensorflow
  - other
frameworks:
  - other
downloads: 6120
stars: 9
---

# ai_model_hub_25_Q3

> ai_model_hub_25_Q3 - cix 在 ModelScope 开源的模型。The CIX AI Model Hub Models are a collection of state-of-the-art machine learning models optimized for deployment on CIX SOCs.

- **Repository**: cix/ai_model_hub_25_Q3
- **Parameters**: 1.2B
- **Downloads**: 6120
- **Stars**: 9
- **Last updated**: 2025-10-10

Source: https://www.modelscope.cn/models/cix/ai_model_hub_25_Q3

---

# CIX AI Model Hub


The CIX AI Model Hub Models are a collection of state-of-the-art machine learning models optimized for deployment on CIX SOCs.

## Setup

### Install Python Package

The package is available via pip and apt:

```shell
apt install libpython3-dev
pip install -r requirements.txt
```

## Getting Started

### Export and Run A Model on a Physical Device

All models in the model hub can be compiled or imported from our pre-built git repo and then run inference on a CIX SOC powered device.

### End-To-End Model Samples

**Python** applications are defined for all models.

**These apps are optimized to be an easy-to-follow example, rather than to minimize prediction time.**

_End-to-end_ samples:

1. **Preprocess** human-readable input into model input
2. Run **model inference**
3. **Postprocess** model output to a human-readable format


All the models sample codes that can run the model _end-to-end_ on a CIX SOC powered device:

```shell
python3 inference_npu.py
```
Also there are end-to-end samples run locally on host X86 or on CIX SOCs via OnnxRuntime.
```shell
python3 inference_onnx.py
```


## LICENSE

CIX  AI Model Hub  is licensed under Apache-2.0.