---
title: OpAgent-32B-Q4
canonical_url: "https://www.modelscope.cn/models/codefuse-ai/OpAgent-32B-Q4"
md_url: "https://www.modelscope.cn/models/codefuse-ai/OpAgent-32B-Q4.md"
repository: codefuse-ai/OpAgent-32B-Q4
last_updated: 2026-03-13
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
base_model:
  - Qwen/Qwen3-VL-32B-Thinking
base_model_relation: quantized
library_name:
  - gguf
  - pytorch
frameworks:
  - Pytorch
language:
  - en
downloads: 161
stars: 1
tags:
  - vlm
  - web-agent
  - opagent
  - gguf
---

# OpAgent-32B-Q4

> OpAgent-32B-Q4 - codefuse-ai 在 ModelScope 开源的模型。OpAgent-32B-Q4 is the 4-bit quantized version of OpAgent-32B， optimized to run efficiently on a single 24GB GPU. OpAgent-32B is a powerful, open-source Vision-Language Model (VLM) specifically fine-tuned for…

codefuse-ai/OpAgent-32B-Q4 是 ModelScope 魔搭社区上的image-text-to-text模型，采用 apache-2.0 许可，基于 Qwen/Qwen3-VL-32B-Thinking 构建。

- **Repository**: codefuse-ai/OpAgent-32B-Q4
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Base model**: Qwen/Qwen3-VL-32B-Thinking
- **Tags**: vlm, web-agent, opagent, gguf
- **Downloads**: 161
- **Stars**: 1
- **Last updated**: 2026-03-13

Source: https://www.modelscope.cn/models/codefuse-ai/OpAgent-32B-Q4

---

# OpAgent-32B-Q4

<!-- Provide a quick summary of what the model is/does. -->
**OpAgent-32B-Q4** is the 4-bit quantized version of **OpAgent-32B**， optimized to run efficiently on a single 24GB GPU. **OpAgent-32B** is a powerful, open-source Vision-Language Model (VLM) specifically fine-tuned for autonomous web navigation. It serves as the core single-model engine within the broader **[OpAgent project](https://github.com/codefuse-ai/OpAgent)**.




## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->

- **Base Model:** `Qwen3-VL-32B-Thinking`
- **Fine-tuning Strategy:** Hierarchical Multi-Task SFT followed by Online Agentic RL with a Hybrid Reward mechanism.
- **Primary Task:** Autonomous web navigation and task execution.
- **Input:** A combination of a natural language task description and a webpage screenshot.
- **Output:** A JSON-formatted action (e.g., `click`, `type`, `scroll`) or a final answer.

### Model Sources [optional]

<!-- Provide the basic links for the model. -->

- **Repository:** [https://github.com/codefuse-ai/OpAgent]



## Uses

This model is designed to be used as a web agent. The primary way to run it is through a high-performance inference engine like **vLLM**, as demonstrated in our [single-model usage guide](https://github.com/codefuse-ai/OpAgent/tree/main/opagent_single_model).
For a complete, interactive agent implementation, please see the code in the [`opagent_single_model`](https://github.com/codefuse-ai/OpAgent/tree/main/opagent_single_model) directory of our repository.

## Citation

If you use `OpAgent-32B` or the `OAgent` framework in your research, please cite our work:

```bibtex
@misc{opagent2026,
  author = {CodeFuse-AI Team},
  title = {OpAgent: Operator Agent for Web Navigation},
  year = {2026},
  publisher = {GitHub},
  howpublished = {\url{https://github.com/codefuse-ai/OpAgent}},
  url = {https://github.com/codefuse-ai/OpAgent}
}