JIANG
No estimate
No hardware requirements for this model
This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.
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
- K.D. Feddersen (KDF)
- Organisation type
- Industry
- Country
- China
- Published
- 1 August 2023
- Authors
- Qinhua Duan, Wenchao Gu, Yujia Chen, Wenxin Mao, Zewen Tian, Hui Cao
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Language modeling
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.
- Training data
- 466,720,000,000 tokens
- Batch size
- 6,000,000
467B tokens (inferred from Table 1). It's a mix of Chinese and English text, I'll use our standard 1:1 token:words ratio for Chinese.
"During the training process, we employed a large batch size of 6 million tokens to enhance the model’s stability"
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
- 4 × 10²² FLOP
- How it was established
- Hardware
"The training was conducted using 96 A100 80G GPUs, and the entire process took approximately 52 days." 312 teraflop/s * 96 * 52 * 24 * 3600 * 0.3 = 4e22
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 SXM4 80 GB
- Chips used
- 96
- Wall-clock time
- 1,200 hours (50 days)
- Power draw
- 76.3 kW
52 days
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
- Open — downloadable
- Model access
- Open weights (unrestricted)
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
- JIANG: Chinese Open Foundation Language Model
- Last updated
- 28 November 2025
What the numbers mean
About this model
JIANG was published by K.D. Feddersen (KDF), in China, in August 2023. The organisation is categorised as industry.
It works in Language, and is recorded as doing language modeling.
The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.
What went into building it
Producing it required around 4 × 10²² FLOP of arithmetic, on NVIDIA A100 SXM4 80 GB, which is a statement about the training budget rather than about inference.
The training set ran to roughly 466,720,000,000 tokens.
Answers
JIANG — common questions
When was JIANG released?
JIANG was published in August 2023. 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 JIANG used for?
JIANG works in Language, and is recorded as handling language modeling. These are the areas it was designed around; they describe intent rather than a hard boundary.
Where can I download JIANG?
The weights for JIANG are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
How much compute was used to train JIANG?
Around 4 × 10²² FLOP, on NVIDIA A100 SXM4 80 GB. 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 JIANG?
We cannot say. JIANG has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.
Is JIANG open source?
Its weights are published, so JIANG can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.
How many parameters does JIANG have?
No parameter count has been published for JIANG, which is why no memory or speed figure appears on this page.
Who created JIANG?
JIANG was published by K.D. Feddersen (KDF), based in China, categorised as industry.
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.