Instructions to use OpenMobile-2/OpenMobile-2-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenMobile-2/OpenMobile-2-9B with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenMobile-2/OpenMobile-2-9B")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("OpenMobile-2/OpenMobile-2-9B")
model = AutoModelForMultimodalLM.from_pretrained("OpenMobile-2/OpenMobile-2-9B", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenMobile-2/OpenMobile-2-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenMobile-2/OpenMobile-2-9B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenMobile-2/OpenMobile-2-9B",
		"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/OpenMobile-2/OpenMobile-2-9B

SGLang

How to use OpenMobile-2/OpenMobile-2-9B 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 "OpenMobile-2/OpenMobile-2-9B" \
    --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": "OpenMobile-2/OpenMobile-2-9B",
		"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 "OpenMobile-2/OpenMobile-2-9B" \
        --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": "OpenMobile-2/OpenMobile-2-9B",
		"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 OpenMobile-2/OpenMobile-2-9B with Docker Model Runner:
```
docker model run hf.co/OpenMobile-2/OpenMobile-2-9B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

HuggingFace | Paper | GitHub | HomePage

Introduction

OpenMobile-2-9B is a mobile GUI agent fine-tuned from Qwen3.5-9B on OpenMobile-Data-v2. It completes Android tasks from screenshots, and can call app-native tools when the foreground app exposes them.

Results

Model	AndroidWorld Pass@1	MobileWorld GUI	MobileGym SR	MobileGym++ Hybrid	SPA-Bench L3
Qwen3.5-9B	54.3	12.8	9.4	12.1	25.5
OpenMobile-1-8B	64.7	17.7	13.7	7.0	--
UI-Venus-1.5-8B	73.7	--	15.4	16.3	29.8
GUI-Owl-1.5-8B	69.0	38.2	17.2	12.6	--
MAI-UI-8B	70.7	27.5	16.8	18.6	--
OpenMobile-2-9B	74.0	38.5	38.3	46.5	48.9

Deploy

The commands below use a context length of 65536 and tensor parallel 2

vLLM

We use vLLM 0.19.1.

pip install vllm==0.19.1

vllm serve OpenMobile-2/OpenMobile-2-9B \
  --tensor-parallel-size 2 \
  --max-model-len 65536 \
  --gpu-memory-utilization 0.90 \
  --max-num-seqs 16 \
  --reasoning-parser qwen3 \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_coder \
  --gdn-prefill-backend triton

SGLang

We use SGLang 0.5.10.post1.

pip install sglang==0.5.10.post1

python -m sglang.launch_server \
  --model-path OpenMobile-2/OpenMobile-2-9B \
  --tp-size 2 \
  --mem-fraction-static 0.8 \
  --context-length 65536 \
  --reasoning-parser qwen3 \
  --tool-call-parser qwen3_coder \
  --enable-multimodal

Citation

If you find this model useful, please cite our paper:

@article{openmobile2,
  title={OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools},
  author={Chenyang Yan and Yingying Zhang and Kanzhi Cheng and Qiushi Sun and Zhengyuan Pan and Zheng Ma and Hang Yan and Yian Wang and Nuo Chen and Jialin Cao and Xingdong Gong and Wenpo Song and Han Chen and Zichen Ding and Fangzhi Xu and Shujian Huang and Xinyu Dai and Yichen Liu and Tiankuo Yao and Bo Wang and Ben Kao and Jianbing Zhang and Lewei Lu and Dahua Lin},
  journal={},
  year={}
}

Downloads last month: 31

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for OpenMobile-2/OpenMobile-2-9B

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

(1004)

this model

Quantizations

1 model