Instructions to use longvideoagent/longvideoagent-qwen3-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use longvideoagent/longvideoagent-qwen3-4b with Transformers:

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

pipe = pipeline("text-generation", model="longvideoagent/longvideoagent-qwen3-4b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("longvideoagent/longvideoagent-qwen3-4b")
model = AutoModelForCausalLM.from_pretrained("longvideoagent/longvideoagent-qwen3-4b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use longvideoagent/longvideoagent-qwen3-4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "longvideoagent/longvideoagent-qwen3-4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "longvideoagent/longvideoagent-qwen3-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/longvideoagent/longvideoagent-qwen3-4b

SGLang

How to use longvideoagent/longvideoagent-qwen3-4b 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 "longvideoagent/longvideoagent-qwen3-4b" \
    --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": "longvideoagent/longvideoagent-qwen3-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "longvideoagent/longvideoagent-qwen3-4b" \
        --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": "longvideoagent/longvideoagent-qwen3-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use longvideoagent/longvideoagent-qwen3-4b with Docker Model Runner:
```
docker model run hf.co/longvideoagent/longvideoagent-qwen3-4b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

LongVideoAgent Qwen3-4B

This repository hosts the released LLM checkpoint for LongVideoAgent, a multi-agent framework for long-video question answering. This model is a Qwen3-4B-based checkpoint used in the LongVideoAgent project.

Overview

This model is trained based on the official repository: longvideoagent/LongVideoAgent.

LongVideoAgent utilizes a multi-agent collaboration framework to decompose complex long-video reasoning into specialized roles. For detailed methodology and agent architecture, please refer to our paper on arXiv: https://arxiv.org/abs/2512.20618.

This checkpoint is intended for use with the official LongVideoAgent codebase and evaluation pipeline.

Performance

On the LongTVQA+ test set, this model achieves an accuracy of 72%, while gpt-4o-mini achieves 74% on the same benchmark.

This demonstrates that our model delivers strong performance, achieving reasoning capabilities comparable to advanced closed-source models while utilizing a significantly smaller parameter size.

Intended Use

Use this model for:

Research on long-video question answering
Reproducing LongVideoAgent experiments
Studying agentic reasoning over long videos

This checkpoint is not a general-purpose video model by itself. For inference and evaluation, please use the official repository:

https://github.com/longvideoagent/LongVideoAgent

Usage

Note on Context Length: This model natively supports a context length of 262,144. If you experience Out-Of-Memory (OOM) errors or have limited VRAM during inference, you can reduce the maximum context length in your vLLM parameters. For example: max_model_len=120000.

Please follow the setup and inference instructions in the official repository and project documentation:

If you use this checkpoint in your work, please also cite the LongVideoAgent paper below.

Citation

@misc{liu2025longvideoagentmultiagentreasoninglong,
  title={LongVideoAgent: Multi-Agent Reasoning with Long Videos},
  author={Runtao Liu and Ziyi Liu and Jiaqi Tang and Yue Ma and Renjie Pi and Jipeng Zhang and Qifeng Chen},
  year={2025},
  eprint={2512.20618},
  archivePrefix={arXiv},
  primaryClass={cs.AI},
  url={[https://arxiv.org/abs/2512.20618](https://arxiv.org/abs/2512.20618)},
}