Instructions to use stepfun-ai/GELab-Zero-4B-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stepfun-ai/GELab-Zero-4B-preview with Transformers:

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

pipe = pipeline("image-text-to-text", model="stepfun-ai/GELab-Zero-4B-preview")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("stepfun-ai/GELab-Zero-4B-preview")
model = AutoModelForMultimodalLM.from_pretrained("stepfun-ai/GELab-Zero-4B-preview", device_map="auto")
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 stepfun-ai/GELab-Zero-4B-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stepfun-ai/GELab-Zero-4B-preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stepfun-ai/GELab-Zero-4B-preview",
		"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/stepfun-ai/GELab-Zero-4B-preview

SGLang

How to use stepfun-ai/GELab-Zero-4B-preview 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 "stepfun-ai/GELab-Zero-4B-preview" \
    --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": "stepfun-ai/GELab-Zero-4B-preview",
		"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 "stepfun-ai/GELab-Zero-4B-preview" \
        --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": "stepfun-ai/GELab-Zero-4B-preview",
		"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 stepfun-ai/GELab-Zero-4B-preview with Docker Model Runner:
```
docker model run hf.co/stepfun-ai/GELab-Zero-4B-preview
```

Improve model card: Add pipeline tag, library name, paper, and project page links

by nielsr HF Staff - opened Dec 19, 2025

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+12

-7

Files changed (1) hide show

README.md +12 -7

README.md CHANGED Viewed

@@ -1,7 +1,9 @@
 ---
-language:
-  - en
-  - zh
 tags:
 - gui-agent
 - phone-use agent
@@ -10,10 +12,14 @@ tags:
 - android
 - multimodal
 - gelab-zero
-license: apache-2.0
-base_model: Qwen/Qwen3-VL-4B-Instruct
 ---
 ## Model Details
 This model is part of the [**GELab-Zero**](https://github.com/stepfun-ai/gelab-zero) project, which aims to accelerate the innovation and application deployment of GUI Agents by providing:
@@ -92,5 +98,4 @@ If you find GELab-Zero-4B-preview useful for your research, please consider citi
       primaryClass={cs.CV},
       url={https://arxiv.org/abs/2512.02423},
 }
-```

 ---
+base_model: Qwen/Qwen3-VL-4B-Instruct
+language:
+- en
+- zh
+license: apache-2.0
 tags:
 - gui-agent
 - phone-use agent
 - android
 - multimodal
 - gelab-zero
+pipeline_tag: image-text-to-text
+library_name: transformers
 ---
+# GELab-Zero-4B-preview
+This model is part of the **GELab-Zero** project, which presents the **Step-GUI Technical Report** [[Paper](https://huggingface.co/papers/2512.15431)] [[Project Page](https://opengelab.github.io/)] [[Code](https://github.com/stepfun-ai/gelab-zero)].
 ## Model Details
 This model is part of the [**GELab-Zero**](https://github.com/stepfun-ai/gelab-zero) project, which aims to accelerate the innovation and application deployment of GUI Agents by providing:
       primaryClass={cs.CV},
       url={https://arxiv.org/abs/2512.02423},
 }
+```