Wu Dao - Wen Yuan
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
- 11 January 2021
- Authors
- Liu Zhiyuan, Huang Minlie, Han Wentao, Liu Yang, Zhu Xiaoyan, Sun Maosong, Zhang Zhengyan, Gu Yuxian, Han Xu, Chen Shengqi, Xiao Chaojun, Yao Yuan, Qi Fanchao, Guan Jian, Ke Pei, Zhou Hao, Sun Zhenbo, Cai Yanzheng, Zeng Guoyang, Tan Zhixing, Qin Yujia, Su Yusheng Si Chenglei, Hu Xueyu, Li Wenhao, Wang Fengyu, Yi Jing, Wang Xiaozhi, Chen Weize, Ding Ning, Zhang Jiajie
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Language modeling/generation
- 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
- 2.6B
- Training data
- tokens
"It has 2.6 billion parameters and is capable of performing cognitive activities such as memorization, comprehension, retrieval, numerical calculation, multi-language, etc." https://medium.com/syncedreview/chinas-gpt-3-baai-introduces-superscale-intelligence-model-wu-dao-1-0-98a573fc4d70
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
- 6.5 × 10²⁰ FLOP
- How it was established
- Hardware
64 Nvidia V100 GPUs for two weeks 64 GPUs * 2.8e13 FLOP/s /GPU * 14*24*60*60s * 0.3 [utilization rate]
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 V100
- Chips used
- 64
- Wall-clock time
- 336 hours (14 days)
- Power draw
- 39.0 kW
two weeks = 336 hours
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Closed — provider access only
- Model access
- API access
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
- Tencent: Facing cognition, Zhiyuan Research Institute and several units released a super-large-scale new pre-training model "Enlightenment·Wenhui"
- Last updated
- 28 November 2025
What the numbers mean
Background
Wu Dao - Wen Yuan was published by Beijing Academy of Artificial Intelligence / BAAI, in China, in January 2021. It comes out of academia.
It works in Language, and is recorded as doing language modeling/generation.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
What went into building it
Producing it required around 6.5 × 10²⁰ FLOP of arithmetic, on NVIDIA V100, which is a statement about the training budget rather than about inference.
Answers
Wu Dao - Wen Yuan — common questions
Who created Wu Dao - Wen Yuan?
Wu Dao - Wen Yuan was published by Beijing Academy of Artificial Intelligence / BAAI, based in China, categorised as academia.
When was Wu Dao - Wen Yuan released?
Wu Dao - Wen Yuan was published in January 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.
What is Wu Dao - Wen Yuan used for?
Wu Dao - Wen Yuan works in Language, and is recorded as handling language modeling/generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
How much compute was used to train Wu Dao - Wen Yuan?
Around 6.5 × 10²⁰ FLOP, on NVIDIA V100. 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.
What GPU do I need to run Wu Dao - Wen Yuan?
None. Wu Dao - Wen Yuan 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.
Is Wu Dao - Wen Yuan open source?
No. Wu Dao - Wen Yuan has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does Wu Dao - Wen Yuan have?
Wu Dao - Wen Yuan has 2.6B parameters. "It has 2.6 billion parameters and is capable of performing cognitive activities such as memorization, comprehension, retrieval, numerical calculation, multi-language, etc." 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.
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.