Instructions to use microsoft/GUI-Actor-7B-Qwen2-VL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/GUI-Actor-7B-Qwen2-VL with Transformers:

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

pipe = pipeline("image-text-to-text", model="microsoft/GUI-Actor-7B-Qwen2-VL")
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 AutoProcessor, Qwen2VLForConditionalGenerationWithPointer

processor = AutoProcessor.from_pretrained("microsoft/GUI-Actor-7B-Qwen2-VL")
model = Qwen2VLForConditionalGenerationWithPointer.from_pretrained("microsoft/GUI-Actor-7B-Qwen2-VL")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use microsoft/GUI-Actor-7B-Qwen2-VL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/GUI-Actor-7B-Qwen2-VL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/GUI-Actor-7B-Qwen2-VL",
		"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/microsoft/GUI-Actor-7B-Qwen2-VL

SGLang

How to use microsoft/GUI-Actor-7B-Qwen2-VL 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 "microsoft/GUI-Actor-7B-Qwen2-VL" \
    --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": "microsoft/GUI-Actor-7B-Qwen2-VL",
		"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 "microsoft/GUI-Actor-7B-Qwen2-VL" \
        --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": "microsoft/GUI-Actor-7B-Qwen2-VL",
		"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 microsoft/GUI-Actor-7B-Qwen2-VL with Docker Model Runner:
```
docker model run hf.co/microsoft/GUI-Actor-7B-Qwen2-VL
```

qianhuiwu commited on Jun 3, 2025

Commit

609d191

verified ·

1 Parent(s): 1b198a2

update model card.

Browse files

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -8,14 +8,14 @@ base_model:
 - [GUI-Actor-7B-Qwen2-VL](https://huggingface.co/microsoft/GUI-Actor-7B-Qwen2-VL)
 - [GUI-Actor-2B-Qwen2-VL](https://huggingface.co/microsoft/GUI-Actor-2B-Qwen2-VL)
-- [GUI-Actor-7B-Qwen2.5-VL](https://huggingface.co/microsoft/GUI-Actor-7B-Qwen2.5-VL)
-- [GUI-Actor-3B-Qwen2.5-VL](https://huggingface.co/microsoft/GUI-Actor-3B-Qwen2.5-VL)
 - [GUI-Actor-Verifier-2B](https://huggingface.co/microsoft/GUI-Actor-Verifier-2B)
-This model was introduced in the paper [**GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents** (Wu et al, 2025)](https://github.com/microsoft/GUI-Actor).
 It is developed based on [Qwen2-VL-7B-Instruct ](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct), augmented by an attention-based action head and finetuned to perform GUI grounding using the dataset [here (coming soon)]().
-For more details on model design and evaluation, please check the project page at [GUI-Actor](https://aka.ms/GUI-Actor).
 ## 📊 Performance Comparison on GUI Grounding Benchmarks
 Table 1. Main results on ScreenSpot-Pro, ScreenSpot, and ScreenSpot-v2 with **Qwen2-VL** as the backbone. † indicates scores obtained from our own evaluation of the official models on Huggingface.
@@ -118,7 +118,7 @@ print(f"Predicted click point: [{round(px, 4)}, {round(py, 4)}]")
 # Predicted click point: [0.9709, 0.1548]
 ```
-## Citation
 ```
 @article{wu2025guiactor,
     title={GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents},

 - [GUI-Actor-7B-Qwen2-VL](https://huggingface.co/microsoft/GUI-Actor-7B-Qwen2-VL)
 - [GUI-Actor-2B-Qwen2-VL](https://huggingface.co/microsoft/GUI-Actor-2B-Qwen2-VL)
+- [GUI-Actor-7B-Qwen2.5-VL (coming soon)](https://huggingface.co/microsoft/GUI-Actor-7B-Qwen2.5-VL)
+- [GUI-Actor-3B-Qwen2.5-VL (coming soon)](https://huggingface.co/microsoft/GUI-Actor-3B-Qwen2.5-VL)
 - [GUI-Actor-Verifier-2B](https://huggingface.co/microsoft/GUI-Actor-Verifier-2B)
+This model was introduced in the paper [**GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents**](https://aka.ms/GUI-Actor).
 It is developed based on [Qwen2-VL-7B-Instruct ](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct), augmented by an attention-based action head and finetuned to perform GUI grounding using the dataset [here (coming soon)]().
+For more details on model design and evaluation, please check: [🏠 Project Page](https://aka.ms/GUI-Actor) | [💻 Github Repo](https://github.com/microsoft/GUI-Actor) | [📑 Paper]().
 ## 📊 Performance Comparison on GUI Grounding Benchmarks
 Table 1. Main results on ScreenSpot-Pro, ScreenSpot, and ScreenSpot-v2 with **Qwen2-VL** as the backbone. † indicates scores obtained from our own evaluation of the official models on Huggingface.
 # Predicted click point: [0.9709, 0.1548]
 ```
+## 📝 Citation
 ```
 @article{wu2025guiactor,
     title={GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents},