Instructions to use models123/Tongyi-DeepResearch-30B-A3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use models123/Tongyi-DeepResearch-30B-A3B with Transformers:

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

pipe = pipeline("text-generation", model="models123/Tongyi-DeepResearch-30B-A3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("models123/Tongyi-DeepResearch-30B-A3B")
model = AutoModelForCausalLM.from_pretrained("models123/Tongyi-DeepResearch-30B-A3B")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use models123/Tongyi-DeepResearch-30B-A3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "models123/Tongyi-DeepResearch-30B-A3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "models123/Tongyi-DeepResearch-30B-A3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/models123/Tongyi-DeepResearch-30B-A3B

SGLang

How to use models123/Tongyi-DeepResearch-30B-A3B 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 "models123/Tongyi-DeepResearch-30B-A3B" \
    --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": "models123/Tongyi-DeepResearch-30B-A3B",
		"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 "models123/Tongyi-DeepResearch-30B-A3B" \
        --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": "models123/Tongyi-DeepResearch-30B-A3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use models123/Tongyi-DeepResearch-30B-A3B with Docker Model Runner:
```
docker model run hf.co/models123/Tongyi-DeepResearch-30B-A3B
```

Introduction

We present Tongyi DeepResearch, an agentic large language model featuring 30 billion total parameters, with only 3 billion activated per token. Developed by Tongyi Lab, the model is specifically designed for long-horizon, deep information-seeking tasks. Tongyi-DeepResearch demonstrates state-of-the-art performance across a range of agentic search benchmarks, including Humanity's Last Exam, BrowserComp, BrowserComp-ZH, WebWalkerQA, GAIA, xbench-DeepSearch and FRAMES.

More details can be found in our 📰 Tech Blog.

Key Features

⚙️ Fully automated synthetic data generation pipeline: We design a highly scalable data synthesis pipeline, which is fully automatic and empowers agentic pre-training, supervised fine-tuning, and reinforcement learning.
🔄 Large-scale continual pre-training on agentic data: Leveraging diverse, high-quality agentic interaction data to extend model capabilities, maintain freshness, and strengthen reasoning performance.
🔁 End-to-end reinforcement learning: We employ a strictly on-policy RL approach based on a customized Group Relative Policy Optimization framework, with token-level policy gradients, leave-one-out advantage estimation, and selective filtering of negative samples to stabilize training in a non‑stationary environment.
🤖 Agent Inference Paradigm Compatibility: At inference, Tongyi-DeepResearch is compatible with two inference paradigms: ReAct, for rigorously evaluating the model's core intrinsic abilities, and an IterResearch-based 'Heavy' mode, which uses a test-time scaling strategy to unlock the model's maximum performance ceiling.

Download

You can download the model then run the inference scipts in https://github.com/Alibaba-NLP/DeepResearch.

@misc{tongyidr,
  author={Tongyi DeepResearch Team},
  title={Tongyi DeepResearch: A New Era of Open-Source AI Researchers},
  year={2025},
  howpublished={\url{https://github.com/Alibaba-NLP/DeepResearch}}
}

Downloads last month: 4

Safetensors

Model size

31B params

Tensor type

BF16