---
title: Tongyi-DeepResearch-30B-A3B
canonical_url: "https://www.modelscope.cn/models/iic/Tongyi-DeepResearch-30B-A3B"
md_url: "https://www.modelscope.cn/models/iic/Tongyi-DeepResearch-30B-A3B.md"
repository: iic/Tongyi-DeepResearch-30B-A3B
chinese_name: "通义-DeepResearch-30B-A3B"
last_updated: 2025-10-10
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen3_moe
architectures:
  - Qwen3MoeForCausalLM
parameters: 30.5B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - Pytorch
language:
  - en
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 217126
stars: 114
---

# Tongyi-DeepResearch-30B-A3B

> Tongyi-DeepResearch-30B-A3B - iic 在 ModelScope 开源的模型。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…

iic/Tongyi-DeepResearch-30B-A3B 是 ModelScope 魔搭社区上的 30.5B 参数text-generation模型，采用 apache-2.0 许可，可用 deploy_task text/emb、lmdeploy_turbomind 0.9.1、sglang 0.5.2 部署。

- **Repository**: iic/Tongyi-DeepResearch-30B-A3B
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 30.5B
- **Inference backends**: deploy_task text/emb, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 217126
- **Stars**: 114
- **Last updated**: 2025-10-10

Source: https://www.modelscope.cn/models/iic/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](https://tongyi-agent.github.io/blog/introducing-tongyi-deep-research).

![image/png](https://cdn-uploads.huggingface.co/production/uploads/63fc4c00a3c067e62899d32b/OhQCYYJu1LhrS446Qct5D.png)

## 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.


```bibtex
@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}}
}
```