BigRNA
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
- DeepGenomics
- Organisation type
- Industry
- Country
- Canada
- Published
- 27 September 2023
- Authors
- Albi Celaj, Alice Jiexin Gao, Tammy T.Y. Lau, Erle M. Holgersen, Alston Lo, Varun Lodaya, Christopher B. Cole, Robert E. Denroche, Carl Spickett, Omar Wagih, Pedro O. Pinheiro, Parth Vora, Pedrum Mohammadi-Shemirani, Steve Chan, Zach Nussbaum, Xi Zhang, Helen Zhu, Easwaran Ramamurthy, Bhargav Kanuparthi, Michael Iacocca, Diane Ly, Ken Kron, Marta Verby, Kahlin Cheung-Ong, Zvi Shalev, Brandon Vaz,…
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- Drug discovery, Protein-RNA binding affinity prediction, Gene expression profile 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.
- Parameters
- 2B
- Training data
- 1,000,000,000,000 tokens
2B
"trained on thousands of datasets comprising one trillion genomic signals"
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
- 1.2 × 10²² FLOP
- How it was established
- Operation counting
6 FLOP/parameter/token * 2000000000 parameters * 1000000000000 tokens = 1.2e+22 FLOP "Likely" confidence because I amnot sure that "signals" correspond directly to gradient updates
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
- Closed — provider access only
- Model access
- Unreleased
- Training code
- Unreleased
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
- An RNA foundation model enables discovery of disease mechanisms and candidate therapeutics
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
BigRNA was published by DeepGenomics, in the country recorded as Canada, during September 2023. The category the publisher falls under is industry.
It works in the domain of Biology, and is recorded as performing the task of drug discovery, Protein-RNA binding affinity prediction, Gene expression profile generation.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Training and provenance
Training it took a computation budget of roughly 1.2 × 10²² FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
The training set ran to roughly 1,000,000,000,000 tokens of text.
Answers
BigRNA — common questions
BigRNA— how many parameters does it have?
It has a parameter count of 2B. 2B. 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.
BigRNA— who created it?
It was published by DeepGenomics, based in Canada, an organisation categorised as industry.
BigRNA— when was it released?
It was published in September 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.
BigRNA— what is it used for?
It works in the domain of Biology, and is recorded as handling the task of drug discovery, Protein-RNA binding affinity prediction, Gene expression profile generation. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.
BigRNA— how much compute was used to train it?
Training consumed around 1.2 × 10²² FLOP. 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.
BigRNA— 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.
BigRNA— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
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.