Wu Dao - Wen Lan

Closed weights Beijing Academy of Artificial Intelligence / BAAI 1B parameters March 2021

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Beijing Academy of Artificial Intelligence / BAAI
Organisation type
Academia
Country
China
Published
1 March 2021
Authors
Wen Jirong, Song Ruihua, Lu Zhiwu, Jin Qin, Zhao Xin, Pang Liang, Lan Yanyan, Dou Zhicheng, Gao Yizhao, Huo Yuqi, Lu Haoyu, Wen Jingyuan, Yang Guoxing, Song Haoyang, Zhang Manli, Zhang Liang, Hu Anwen, Li Ruichen, Song Yuqing, Zhao Jinming, Zhao Yida, Fei Nanyi, Sun Yuchong, Jin Chuhao, Hong Xin, Cui Wanqing, Hou Danyang, Li Yingyan, Xi Zongzheng, Liu Guangzhen, Liu Peiyu, Gong Zheng, Li Juny

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Multimodal, Vision, Language
Task
Image captioning
Approach
Self-supervised learning

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
1B

"Currently, the model has 1 billion parameters and is trained on 50 million graphic pairs collected from open sources." https://medium.com/syncedreview/chinas-gpt-3-baai-introduces-superscale-intelligence-model-wu-dao-1-0-98a573fc4d70

Training data
tokens

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute
7.2 × 10²¹ FLOP

128 Nvidia A100 GPUs for 7 days 128 GPUs * 3.1e14 FLOP/s /GPU * 7*24*60*60s* 0.3 [utilization rate]

How it was established
Hardware

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware
NVIDIA A100
Chips used
128
Wall-clock time
168 hours (7 days)
Power draw
103.8 kW

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Confident

Sources

Where this record came from and when it was last checked.

Reference
China's GPT-3? BAAI Introduces Superscale Intelligence Model 'Wu Dao 1.0'
Last updated
28 November 2025

What the numbers mean

Where it came from

Wu Dao - Wen Lan was published by Beijing Academy of Artificial Intelligence / BAAI, in China, in March 2021. The organisation is categorised as academia.

It works in Multimodal, Vision, Language, and is recorded as doing image captioning.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

How it was trained

Training it took roughly 7.2 × 10²¹ FLOP of computation, on NVIDIA A100 — a measure of what producing the model cost, not of how fast it answers.

Answers

Wu Dao - Wen Lan — common questions

01

Is Wu Dao - Wen Lan open source?

The licensing for Wu Dao - Wen Lan was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

02

How many parameters does Wu Dao - Wen Lan have?

Wu Dao - Wen Lan has 1B parameters. "Currently, the model has 1 billion parameters and is trained on 50 million graphic pairs collected from open sources." https://medium.com/syncedreview/chinas-gpt-3-baai-introduces-superscale-intelligence-model-wu-dao-1-0-98a573fc4d70. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

03

Who created Wu Dao - Wen Lan?

Wu Dao - Wen Lan was published by Beijing Academy of Artificial Intelligence / BAAI, based in China, categorised as academia.

04

When was Wu Dao - Wen Lan released?

Wu Dao - Wen Lan was published in March 2021. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

What is Wu Dao - Wen Lan used for?

Wu Dao - Wen Lan works in Multimodal, Vision, Language, and is recorded as handling image captioning. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

06

How much compute was used to train Wu Dao - Wen Lan?

Around 7.2 × 10²¹ FLOP, on NVIDIA A100. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

07

What GPU do I need to run Wu Dao - Wen Lan?

None. Wu Dao - Wen Lan is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.