Instructions to use xlangai/OpenCUA-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xlangai/OpenCUA-7B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="xlangai/OpenCUA-7B", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("xlangai/OpenCUA-7B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use xlangai/OpenCUA-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xlangai/OpenCUA-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xlangai/OpenCUA-7B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/xlangai/OpenCUA-7B

SGLang

How to use xlangai/OpenCUA-7B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "xlangai/OpenCUA-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xlangai/OpenCUA-7B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "xlangai/OpenCUA-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xlangai/OpenCUA-7B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use xlangai/OpenCUA-7B with Docker Model Runner:
```
docker model run hf.co/xlangai/OpenCUA-7B
```

Practicalities of fast inference (NOT OSWorld!)

by sujitvasanth - opened Sep 7, 2025

Discussion

sujitvasanth

Sep 7, 2025

Thanks lots of publicity on channels like youtube and twitter. But no examples of how to use!
Rather than use OSWorld (tried and very slow cumbersome) I made my own pipeline on ubuntu 20.04 running a second screen and VNC.
I worote a quick VNC client using asyncvnc. Much more efficient (no full VM overhead and no multiple servers on the VM!) and screen shots faster than real time in my rtx3090 setup. I customised the VNC client to pull the screenshots and run inference on them. I think ithsi is a better longterm solution than pyautogui.

Firstly the requirments file you refer to in the model card is not available. (unless you are referring to https://github.com/xlang-ai/OpenCUA/blob/main/model/requirement.txt)
I was able to run in python3.12, pytorch2.4(CUDA), transformers 4.49 so those requirments are not actually the minimal.
I foundin the grounding examples whatever I prompted I was still getting clicks (never text)

Im just in the process of implementing CoT
For speed increase has anyone tried BnB quantisation or half precision inference (havent looked at the detailed architecture to see if these are even possible yet)

xywang626

XLang NLP Lab org Sep 8, 2025

Wow, this is very cool!

If you want to build an executable agent, you may follow OpenCUA's agent design in OSWorld (https://github.com/xlang-ai/OSWorld/blob/main/mm_agents/opencua_agent.py)
The system prompts in the repo follows our training data, so the model may output other kinds of actions.

Best,
Xinyuan

xywang626 changed discussion status to closed Feb 1

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment