Wu Dao - Wen Hui
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
- Tang Jie, Yang Zhilin, Yang Hongxia, Du Zhengxiao, Ding Ming, Zou Xu, Qiu Jiezhong, Qian Yujie, Yinda, Zhong Qingyang, Yu Jifan, Liu Xiao, Zheng Yanan, He Jiaao, Zeng Aohan, Hong Wenyi, Yang Zhuoyi, Zheng Wendi, Zhou Jing, Du Jizhong, Guo Zitong, Liu Jing, Zhou Chang, Lin Junyang
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language, Multimodal, Video, Image generation
- Task
- Language modeling/generation, Image generation, Video generation, Text-to-image, Question answering, Visual question answering
- 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
- 11.3B
- Training data
- tokens
"Wu Dao — Wen Hui has reached 11.3 billion parameters, and through simple fine-tuning can generate poetry, make videos, draw pictures, retrieve text, perform complex reasoning, 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
- 1.2 × 10²⁰ FLOP
- How it was established
- Hardware
64 Nvidia V100 GPUs for 2.5 days 64 GPUs * 2.8e13 FLOP/s /GPU * 2.5*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
- 60 hours
- Power draw
- 38.9 kW
2.5 days = 60 hours
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 Hui was published by Beijing Academy of Artificial Intelligence / BAAI, in China, in March 2021. It comes out of academia.
It works in Language, Multimodal, Video, Image generation, and is recorded as doing language modeling/generation, Image generation, Video generation, Text-to-image, Question answering, Visual question answering.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
How it was trained
Training it took roughly 1.2 × 10²⁰ FLOP of computation, on NVIDIA V100 — a measure of what producing the model cost, not of how fast it answers.
Answers
Wu Dao - Wen Hui — common questions
What is Wu Dao - Wen Hui used for?
Wu Dao - Wen Hui works in Language, Multimodal, Video, Image generation, and is recorded as handling language modeling/generation, Image generation, Video generation, Text-to-image, Question answering, Visual question answering. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.
How much compute was used to train Wu Dao - Wen Hui?
Around 1.2 × 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 Hui?
None. Wu Dao - Wen Hui 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 Hui open source?
The licensing for Wu Dao - Wen Hui was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
How many parameters does Wu Dao - Wen Hui have?
Wu Dao - Wen Hui has 11.3B parameters. "Wu Dao — Wen Hui has reached 11.3 billion parameters, and through simple fine-tuning can generate poetry, make videos, draw pictures, retrieve text, perform complex reasoning, 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.
Who created Wu Dao - Wen Hui?
Wu Dao - Wen Hui was published by Beijing Academy of Artificial Intelligence / BAAI, based in China, categorised as academia.
When was Wu Dao - Wen Hui released?
Wu Dao - Wen Hui 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.
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.