RoseTTAFold All-Atom (RFAA)
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
- University of Washington,Seoul National University,University of Sheffield
- Organisation type
- Academia,Academia,Academia
- Country
- United States of America, Korea (Republic of), United Kingdom of Great Britain and Northern Ireland
- Published
- 9 October 2023
- Authors
- Rohith Krishna, Jue Wang, Woody Ahern, Pascal Sturmfels, Preetham Venkatesh, Indrek Kalvet, Gyu Rie Lee, Felix S Morey-Burrows, Ivan Anishchenko, Ian R Humphreys, Ryan McHugh, Dionne Vafeados, Xinting Li, George A Sutherland, Andrew Hitchcock, C Neil Hunter, Minkyung Baek, Frank DiMaio, David Baker
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- Protein folding prediction, Proteins
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
- 63,240,960 tokens
Datasets: 121,800 + 112,546 + 12,689 = 247,035 "All examples were cropped to have 256 tokens during the initial stages of training and 375 tokens during fine-tuning." 247035 * 256 =63,240,960 tokens
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
- 2.1 × 10²⁰ FLOP
- How it was established
- Hardware
Supplementary material: "This took 8 days on 8 NVIDIA A6000 GPUs." 8 GPUS *3.87E+13 FLOPS/A6000 *60 * 60 * 24 * 8 days
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 RTX A6000
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)
- Training code
- Open source
MIT-like license. inference code + training hyperparams: https://github.com/baker-laboratory/RoseTTAFold-All-Atom?tab=License-1-ov-file#readme
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Why it is tracked
- SOTA improvement
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- Generalized Biomolecular Modeling and Design with RoseTTAFold All-Atom
- Last updated
- 11 February 2026
What the numbers mean
What this model is
RoseTTAFold All-Atom (RFAA) was published by University of Washington,Seoul National University,University of Sheffield, in the country recorded as United States of America, during October 2023. The category the publisher falls under is academia,Academia,Academia.
It works in the domain of Biology, and is recorded as performing the task of protein folding prediction, Proteins.
The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.
Training and provenance
Producing it required arithmetic totalling around 2.1 × 10²⁰ FLOP, on hardware recorded as NVIDIA RTX A6000. That figure measures what producing the model cost, and has no bearing on how fast it answers.
The training set ran to roughly 63,240,960 tokens of text.
Its inclusion criterion: sOTA improvement.
Answers
RoseTTAFold All-Atom (RFAA) — common questions
RoseTTAFold All-Atom (RFAA)— what is it used for?
It works in the domain of Biology, and is recorded as handling the task of protein folding prediction, Proteins. These are the areas it was designed around; they describe intent rather than a hard boundary.
RoseTTAFold All-Atom (RFAA)— where can I download it?
The weights are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
RoseTTAFold All-Atom (RFAA)— how much compute was used to train it?
Training consumed around 2.1 × 10²⁰ FLOP, on hardware recorded as NVIDIA RTX A6000. 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.
RoseTTAFold All-Atom (RFAA)— what GPU do I need to run it?
We cannot say. It 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.
RoseTTAFold All-Atom (RFAA)— is it open source?
Its weights are published, so it 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.
RoseTTAFold All-Atom (RFAA)— how many parameters does it have?
No parameter count has been published for it, which is why no memory or speed figure appears on this page.
RoseTTAFold All-Atom (RFAA)— who created it?
It was published by University of Washington,Seoul National University,University of Sheffield, based in United States of America, an organisation categorised as academia,Academia,Academia.
RoseTTAFold All-Atom (RFAA)— when was it released?
It was published in October 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.
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.