---
title: Skywork-R1V3-38B-GGUF
canonical_url: "https://www.modelscope.cn/models/Skywork/Skywork-R1V3-38B-GGUF"
md_url: "https://www.modelscope.cn/models/Skywork/Skywork-R1V3-38B-GGUF.md"
repository: Skywork/Skywork-R1V3-38B-GGUF
last_updated: 2025-07-23
license: mit
library_name:
  - gguf
  - pytorch
frameworks:
  - pytorch
downloads: 276
stars: 0
tags:
  - gguf
---

# Skywork-R1V3-38B-GGUF

> Skywork-R1V3-38B-GGUF - Skywork 在 ModelScope 开源的模型。🧠 Skywork-R1V3-38B - GGUF Quantized

Skywork/Skywork-R1V3-38B-GGUF 是 ModelScope 魔搭社区上的机器学习模型，采用 mit 许可。

- **Repository**: Skywork/Skywork-R1V3-38B-GGUF
- **License**: mit
- **Tags**: gguf
- **Downloads**: 276
- **Stars**: 0
- **Last updated**: 2025-07-23

Source: https://www.modelscope.cn/models/Skywork/Skywork-R1V3-38B-GGUF

---

# 🧠 Skywork-R1V3-38B - GGUF Quantized

This repository provides a `GGUF` quantized version of the [Skywork-R1V3-38B](https://huggingface.co/Skywork/Skywork-R1V3-38B) model, converted using the latest `master` branch of [llama.cpp](https://github.com/ggerganov/llama.cpp). This version is optimized for **fast and memory-efficient local inference** on CPU or GPU.

## 💻 How to Use

You can run this model with [`llama.cpp`](https://github.com/ggerganov/llama.cpp):

```bash
./llama-server -m /path/to/Skywork-R1V3-38B-Q8_0.gguf --mmproj /path/to/mmproj-Skywork-R1V3-38B-f16.gguf --port 8080
```
You can now use OpenAI-compatible tools (like curl) to query the model:

```bash
BASE64_IMAGE=$(base64 -w 0 /path/to/image)
curl -X POST http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Skywork-R1V3",
    "messages": [
      {
        "role": "user",
        "content": [
          {"type": "text", "text": "Please describe this image."},
          {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,'"${BASE64_IMAGE}"'" }}
        ]
      }
    ],
    "temperature": 0.7,
    "max_tokens": 512
  }'

```

## Citation
If you use this model in your research, please cite:
```bibtex
@misc{shen2025skyworkr1v3technicalreport,
      title={Skywork-R1V3 Technical Report}, 
      author={Wei Shen and Jiangbo Pei and Yi Peng and Xuchen Song and Yang Liu and Jian Peng and Haofeng Sun and Yunzhuo Hao and Peiyu Wang and Jianhao Zhang and Yahui Zhou},
      year={2025},
      eprint={2507.06167},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2507.06167}, 
}
```