README.md

---
pipeline_tag: image-text-to-text
library_name: transformers
language:
- en
base_model:
- Qwen/Qwen3-VL-30B-A3B-Instruct
tags:
- browser_use
---


# BU-30B-A3B-Preview

<picture>
  <source media="(prefers-color-scheme: light)" srcset="https://github.com/user-attachments/assets/2ccdb752-22fb-41c7-8948-857fc1ad7e24"">
  <source media="(prefers-color-scheme: dark)" srcset="https://github.com/user-attachments/assets/774a46d5-27a0-490c-b7d0-e65fcbbfa358">
  <img alt="Shows a black Browser Use Logo in light color mode and a white one in dark color mode." src="https://github.com/user-attachments/assets/2ccdb752-22fb-41c7-8948-857fc1ad7e24"  width="full">
</picture>

Meet BU-30B-A3B-Preview — bringing SoTA Browser Use capabilities in a small model that can be hosted on a single GPU.

This model is heavily trained to be used with [browser-use OSS library](https://github.com/browser-use/browser-use) and provides comprehensive browsing capabilities with superior DOM understanding and visual reasoning.

## Quickstart (BU Cloud)

You can directly use this model at BU Cloud. Simply

1. Get your API key from [BU Cloud](https://cloud.browser-use.com/new-api-key?utm_source=hugging-face)
2. Set environment variable: export BROWSER_USE_API_KEY="your-key"
3. Install the browser-use library following the instructions [here](https://github.com/browser-use/browser-use) and run

```python
from dotenv import load_dotenv
from browser_use import Agent, ChatBrowserUse
load_dotenv()

llm = ChatBrowserUse(
	model='browser-use/bu-30b-a3b-preview',  # BU Open Source Model!!
)

agent = Agent(
	task='Find the number of stars of browser-use and stagehand. Tell me which one has more stars :)',
	llm=llm,
    flash_mode=True
)
agent.run_sync()
```

## Quickstart (vLLM)

We recommend using this model with [vLLM](https://github.com/vllm-project/vllm).

#### Installation

Make sure to install **vllm >= 0.12.0**:

```
pip install vllm --upgrade
```

#### Serve

A simple launch command is:

```bash
vllm serve browser-use/bu-30b-a3b-preview \
  --max-model-len 65536 \
  --host 0.0.0.0 \
  --port 8000
```

which will create an OpenAI compatible endpoint at localhost that you can use with.

```python
from dotenv import load_dotenv
from browser_use import Agent, ChatOpenAI
load_dotenv()

llm = ChatOpenAI(
    base_url='http://localhost:8000/v1',
    model='browser-use/bu-30b-a3b-preview',
    temperature=0.6,
    top_p=0.95,
    dont_force_structured_output=True, # speed up by disabling structured output
)

agent = Agent(
    task='Find the number of stars of browser-use and stagehand. Tell me which one has more stars :)',
    llm=llm,
)
agent.run_sync()
```

## Model Details

| Property | Value |
|----------|-------|
| **Base Model** | Qwen/Qwen3-VL-30B-A3B-Instruct |
| **Parameters** | 30B total, 3B active (MoE) |
| **Context Length** | 65,536 tokens |
| **Architecture** | Vision-Language Model (Mixture of Experts) |

## Links

- 🌐 [Browser Use Cloud](https://cloud.browser-use.com)
- 📚 [Documentation](https://docs.browser-use.com)
- 💻 [GitHub](https://github.com/browser-use/browser-use)
- 💬 [Discord](https://link.browser-use.com/discord)