IDPFold
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
- Shandong University,BioMap Research,Fuzhou University,Shanghai Jiao Tong University
- Organisation type
- Academia,Industry,Academia,Academia
- Country
- China
- Published
- 13 September 2024
- Authors
- Junjie Zhu, Zhengxin Li, Zhuoqi Zheng, Bo Zhang, Bozitao Zhong, Jie Bai, Xiaokun Hong, Taifeng Wang, Ting Wei, Jianyi Yang, Hai-Feng Chen
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- Protein folding prediction
- Base model
- ESM2-650M
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
- 17.8M
- Training data
- 30,928,500 tokens
Taken from Table 2
Initial Phase: 25,495 sequences × 200 residues = 5,099,000 points Second Phase: 3,880 sequences × 300 residues = 1,164,000 points Total: 5,099,000 + 1,164,000 = 6,263,000 points Rounded: 7.5 million data points
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
- 2.6 × 10²⁰ FLOP
- How it was established
- Hardware
1. Hardware setup: 1x NVIDIA A100 GPU with 3.12×10¹⁴ FLOP/s (fp16_tensor) 2. Training duration: Directly provided as 24 GPU days (9 days initial + 15 days second phase) = 2.0736×10⁶ seconds 3. Utilization rate: 40% 4. Final calculation: 3.12×10¹⁴ FLOP/s × 1 GPU × 2.0736×10⁶ s × 0.4 = 2.6×10²⁰ FLOP
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
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Likely
Sources
Where this record came from and when it was last checked.
- Reference
- Precise Generation of Conformational Ensembles for Intrinsically Disordered Proteins via Fine-tuned Diffusion Models
- Last updated
- 28 November 2025
What the numbers mean
Background
IDPFold was published by Shandong University,BioMap Research,Fuzhou University,Shanghai Jiao Tong University, in the country recorded as China, during September 2024. The category the publisher falls under is academia,Industry,Academia,Academia.
It works in the domain of Biology, and is recorded as performing the task of protein folding prediction.
Its starting point was an existing base model, ESM2-650M. Most models at this scale are adapted from an existing base rather than built from nothing.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
How it was trained
The training run consumed about 2.6 × 10²⁰ FLOP, on hardware recorded as NVIDIA A100. That figure measures what producing the model cost, and has no bearing on how fast it answers.
The training set ran to roughly 30,928,500 tokens of text.
Answers
IDPFold — common questions
IDPFold— who created it?
It was published by Shandong University,BioMap Research,Fuzhou University,Shanghai Jiao Tong University, based in China, an organisation categorised as academia,Industry,Academia,Academia.
IDPFold— when was it released?
It was published in September 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
IDPFold— what is it used for?
It works in the domain of Biology, and is recorded as handling the task of protein folding prediction. These are the areas it was designed around; they describe intent rather than a hard boundary.
IDPFold— how much compute was used to train it?
Training consumed around 2.6 × 10²⁰ FLOP, on hardware recorded as 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.
IDPFold— what GPU do I need to run it?
None. This 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.
IDPFold— is it open source?
The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
IDPFold— how many parameters does it have?
It has a parameter count of 17.8M. Taken from Table 2. 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.