Instructions to use MCG-NJU/OneStreamer-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MCG-NJU/OneStreamer-4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="MCG-NJU/OneStreamer-4B")
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("MCG-NJU/OneStreamer-4B")
model = AutoModelForMultimodalLM.from_pretrained("MCG-NJU/OneStreamer-4B", 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 MCG-NJU/OneStreamer-4B with vLLM:

Install from pip and serve model

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

SGLang

How to use MCG-NJU/OneStreamer-4B 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 "MCG-NJU/OneStreamer-4B" \
    --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": "MCG-NJU/OneStreamer-4B",
		"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 "MCG-NJU/OneStreamer-4B" \
        --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": "MCG-NJU/OneStreamer-4B",
		"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 MCG-NJU/OneStreamer-4B with Docker Model Runner:
```
docker model run hf.co/MCG-NJU/OneStreamer-4B
```

OneStreamer-4B

Perceive the present. Remember the past. Respond at the right time.

Paper · GitHub · Project page · OneStreamer-1M

OneStreamer-4B is a streaming video-language model initialized from Qwen3-VL-4B-Instruct. It interprets incoming video, records time-grounded evidence, and decides when to respond. The model is introduced in OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction.

Performance

OneStreamer-4B achieves the best aggregate results among the methods compared in the paper on all eight benchmarks. Each benchmark uses its own metric; all values below are higher-is-better.

Benchmark	Metric	Qwen3-VL-4B base	OneStreamer-4B
OVOBench	Overall	58.8	72.1
StreamingBench	Real-Time	81.8	86.9
OVBench	Average	55.4	66.8
ODVBench	Overall	57.6	71.3
ProactiveVideoQA	Average	34.3	48.7
OmniMMI	Average	29.4	36.6
OVO-Timing	Average F1	29.4	41.6
ViSpeak	Average, 0–5 scale	2.41	2.87

The figure and numbers follow the GitHub README. OneStreamer's OmniMMI result uses ASR for AP, SI, MD, and SG; PA is visual-only. See the evaluation settings for full protocols.

Inference

OneStreamer processes video incrementally through a recent visual window, while PHCM retains time-aligned caption memory for later questions. For proactive interaction, the model generates </Silence> to keep observing, </Standby> when more evidence is needed, or </Response> followed by an answer once the observed evidence is sufficient.

See Inference/ on GitHub for the implementation and usage.

Citation

@misc{zeng2026onestreamerunifyingperceptionmemory,
  title={OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction},
  author={Xiangyu Zeng and Yuandong Yang and Zhiqiu Zhang and Yuhan Zhu and Xinhao Li and Qingyi Si and Dingyu Yao and Changlian Ma and Haoran Chen and Xinyu Chen and Yansong Shi and Junhao Zhou and Yifei Li and Jun Zhang and Chuanyu Qin and Chenxu Yang and Xinlei Yu and Kun Ouyang and Yuchen Shao and Qianshan Wei and Changhai Zhou and Jun Gao and Jiaqi Wang and Limin Wang},
  year={2026},
  eprint={2610.01762},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2610.01762}
}