AtomFlow
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
- Peking University,Chinese University of Hong Kong (CUHK),Mila - Quebec AI (originally Montreal Institute for Learning Algorithms),University of Montreal / Université de Montréal,HEC Montreal,CIFAR AI Research
- Organisation type
- Academia,Academia,Academia,Academia,Academia,Research collective
- Country
- China, Hong Kong, Canada
- Published
- 18 September 2024
- Authors
- Junqi Liu, Shaoning Li, Chence Shi, Zhi Yang, Jian Tang
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- Protein generation
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
- tokens
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 GeForce RTX 4090
- Chips used
- 10
- Power draw
- 8.9 kW
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Unknown
- Citations
- 4
Sources
Where this record came from and when it was last checked.
- Reference
- Design of Ligand-Binding Proteins with Atomic Flow Matching
- Last updated
- 25 May 2026
What the numbers mean
About this model
AtomFlow was published by Peking University,Chinese University of Hong Kong (CUHK),Mila - Quebec AI (originally Montreal Institute for Learning Algorithms),University of Montreal / Université de Montréal,HEC Montreal,CIFAR AI Research, in China, in September 2024. It comes out of academia,Academia,Academia,Academia,Academia,Research collective.
It works in Biology, and is recorded as doing protein generation.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
Answers
AtomFlow — common questions
Who created AtomFlow?
AtomFlow was published by Peking University,Chinese University of Hong Kong (CUHK),Mila - Quebec AI (originally Montreal Institute for Learning Algorithms),University of Montreal / Université de Montréal,HEC Montreal,CIFAR AI Research, based in China, categorised as academia,Academia,Academia,Academia,Academia,Research collective.
When was AtomFlow released?
AtomFlow 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.
What is AtomFlow used for?
AtomFlow works in Biology, and is recorded as handling protein generation. These are the areas it was designed around; they describe intent rather than a hard boundary.
What GPU do I need to run AtomFlow?
None. AtomFlow 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 AtomFlow open source?
The licensing for AtomFlow 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 AtomFlow have?
No parameter count has been published for AtomFlow, which is why no memory or speed figure appears on this page.
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.