---
title: UniScientist-30B-A3B
canonical_url: "https://www.modelscope.cn/models/UniPatAI/UniScientist-30B-A3B"
md_url: "https://www.modelscope.cn/models/UniPatAI/UniScientist-30B-A3B.md"
repository: UniPatAI/UniScientist-30B-A3B
last_updated: 2026-03-12
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: 97
stars: 1
---

# UniScientist-30B-A3B

> UniScientist-30B-A3B - UniPatAI 在 ModelScope 开源的模型。We present UniScientist, an agentic large language model featuring 30 billion total parameters, with only 3 billion activated per token. Developed by UniPat AI, the model is specifically designed for…

UniPatAI/UniScientist-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**: UniPatAI/UniScientist-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**: 97
- **Stars**: 1
- **Last updated**: 2026-03-12

Source: https://www.modelscope.cn/models/UniPatAI/UniScientist-30B-A3B

---

# Introduction

We present **UniScientist**, an agentic large language model featuring 30 billion total parameters, with only 3 billion activated per token. Developed by UniPat AI, the model is specifically designed for **universal scientific research** tasks spanning 50+ disciplines. UniScientist achieves state-of-the-art performance across a range of research benchmarks, including FrontierScience-Research, FrontierScience-Olympiad, DeepResearch Bench, DeepResearch Bench II, and ResearchRubrics.

More details can be found in our [Blog](https://unipat.ai/blog/UniScientist).

## Key Features

- **Evolving Polymathic Synthesis**: A human-LLM collaborative data paradigm that generates research-grade scientific problems across 50+ disciplines, each accompanied by co-evolved rubrics refined through completeness, consistency, and distinguishability checks.
- **Agentic Research Loop**: The model conducts scientific research by iteratively acquiring evidence, deriving formally-justified results, and updating hypotheses via abductive inference, using tools including `web_search`, `google_scholar`, `page_fetching`, and `code_interpreter`.
- **Report Aggregation**: Given multiple candidate research reports, the model learns to synthesize a consolidated report integrating the best elements, enabling research quality to self-evolve over time.

## Download

You can download the model then run the inference scripts in https://github.com/UniPat-AI/UniScientist.

```bibtex
@misc{unipat2026uniscientist,
  title   = {UniScientist: Advancing Universal Scientific Research Intelligence},
  author  = {UniPat AI Team},
  year    = {2026},
  howpublished = {\url{https://github.com/UniPat-AI/UniScientist}}
}
```