PocketFlow
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
- University of Science and Technology of China (USTC),State Key Laboratory of Cognitive Intelligence,Harvard University
- Organisation type
- Academia,Academia
- Country
- China, United States of America
- Published
- 29 September 2024
- Authors
- Zaixi Zhang, Marinka Zitnik, Qi Liu
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- Protein design, Drug discovery
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
- Epochs
- 20
CrossDocked: 100,000 complexes × (100 residues + 50 atoms) = 15,000,000 MOAD: 40,000 pairs × (100 residues + 50 atoms) = 6,000,000 Total: 15,000,000 + 6,000,000 = 21,000,000 datapoints = 2.1 × 10⁷
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.
- How it was established
- Hardware
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
- Chips used
- 1
- Power draw
- 433 W
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
- Generalized Protein Pocket Generation with Prior-Informed Flow Matching
- Last updated
- 28 November 2025
What the numbers mean
Background
PocketFlow was published by University of Science and Technology of China (USTC),State Key Laboratory of Cognitive Intelligence,Harvard University, in China, in September 2024. The organisation is categorised as academia,Academia.
It works in Biology, and is recorded as doing protein design, Drug discovery.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
Answers
PocketFlow — common questions
What is PocketFlow used for?
PocketFlow works in Biology, and is recorded as handling protein design, Drug discovery. These are the areas it was designed around; they describe intent rather than a hard boundary.
What GPU do I need to run PocketFlow?
None. PocketFlow 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 PocketFlow open source?
The licensing for PocketFlow 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 PocketFlow have?
No parameter count has been published for PocketFlow, which is why no memory or speed figure appears on this page.
Who created PocketFlow?
PocketFlow was published by University of Science and Technology of China (USTC),State Key Laboratory of Cognitive Intelligence,Harvard University, based in China, categorised as academia,Academia.
When was PocketFlow released?
PocketFlow 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.
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.