Yuan 1.0
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
- Inspur
- Organisation type
- Industry
- Country
- China
- Published
- 12 October 2021
- Authors
- Shaohua Wu, Xudong Zhao, Tong Yu, Rongguo Zhang, Chong Shen, Hongli Liu, Feng Li, Hong Zhu, Jiangang Luo, Liang Xu, Xuanwei Zhang, Jun Liu
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Language modeling
- Approach
- Self-supervised learning
- Numerical format
- FP16
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
- 245.7B
- Training data
- 180,000,000,000 tokens
- Batch size
- 6,881,280
Table 2: Parameters of Yuan models. "Parameters (billion)"
"Yuan 1.0 was trained on a new Chinese dataset of 5TB high-quality text that was built on 850TB raw data from Internet." 1 GB ~ 167M words in English or 333M words in Chinese. For a mixed dataset of mostly Chinese, 5TB may be equivalent to around 1T words. Table 2: 180B training tokens
Table 2. Batch size 3360, sequence length 2048. 3360*2048 = 6881280
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
- 3.5 × 10²³ FLOP
- How it was established
- Reported
Table 9: 4095 petaFLOPS-days which equals 3.538*10^23 FLOP https://www.wolframalpha.com/input?i=4095+petaFLOPS+*+1+day
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Chips used
- 2,128
- Hardware utilisation
- HFU 45.0%
- Compute cost
- $591,665
"The Yuan models are trained on a cluster with 2128 GPUs. A stable real performance of 45% of the theoretical peak performance is achieved on this cluster." HFU = 0.4500
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
- Training code
- Unreleased
https://github.com/Shawn-IEITSystems/Yuan-1.0
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Frontier model
- Yes
- Likely above 10²³ FLOP
- Yes
- Why it is tracked
- SOTA improvement
- Record confidence
- Confident
- Citations
- 69
"The zero-shot average scores of both LM and PLM are superior to the SOTA one. On Csldcp, Tnews and Iflytek tasks, we surpass the zero-shot SOTA by a large margin"
Sources
Where this record came from and when it was last checked.
- Reference
- Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot Learning
- Last updated
- 25 May 2026
What the numbers mean
What this model is
Yuan 1.0 was published by Inspur, in China, in October 2021. industry is the category the publisher falls under.
It works in Language, and is recorded as doing language modeling.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
How it was trained
Producing it required around 3.5 × 10²³ FLOP of arithmetic, which is a statement about the training budget rather than about inference.
The training set ran to roughly 180,000,000,000 tokens.
It is tracked in the underlying dataset for one reason in particular: sOTA improvement.
Answers
Yuan 1.0 — common questions
What GPU do I need to run Yuan 1.0?
None. Yuan 1.0 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 Yuan 1.0 open source?
No. Yuan 1.0 has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does Yuan 1.0 have?
Yuan 1.0 has 245.7B parameters. Table 2: Parameters of Yuan models. "Parameters (billion)". 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 Yuan 1.0?
Yuan 1.0 was published by Inspur, based in China, categorised as industry.
When was Yuan 1.0 released?
Yuan 1.0 was published in October 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 Yuan 1.0 used for?
Yuan 1.0 works in Language, and is recorded as handling language modeling. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
How much compute was used to train Yuan 1.0?
Around 3.5 × 10²³ FLOP. 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.
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.