Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Sponsored by
APIMart
browser-use / bu-30b-a3b-preview
Model's Last Updated: April 04 2026
image-text-to-text
Introduction of bu-30b-a3b-preview
Model Details of bu-30b-a3b-preview
BU-30B-A3B-Preview
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 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
- Get your API key from BU Cloud
- Set environment variable: export BROWSER_USE_API_KEY="your-key"
- Install the browser-use library following the instructions here and run
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 .
Installation
Make sure to install vllm >= 0.12.0 :
pip install vllm --upgrade
Serve
A simple launch command is:
vllm serve browser-use/bu-30b-a3b-preview \
--max-model-len 32768 \
--host 0.0.0.0 \
--port 8000
which will create an OpenAI compatible endpoint at localhost that you can use with.
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 | 32,768 tokens |
| Architecture | Vision-Language Model (Mixture of Experts) |
Links
- 🌐 Browser Use Cloud
- 📚 Documentation
- 💻 GitHub
- 💬 Discord
Runs of browser-use bu-30b-a3b-preview on huggingface.co
2.0K
Total runs
22
24-hour runs
-352
3-day runs
-276
7-day runs
417
30-day runs
More Information About bu-30b-a3b-preview huggingface.co Model
Url of bu-30b-a3b-preview
bu-30b-a3b-preview huggingface.co Url
Provider of bu-30b-a3b-preview huggingface.co
Other API from browser-use
Updated:September 22 2025