RNA-FM
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
- Chinese University of Hong Kong (CUHK),Fudan University,Shanghai AI Lab,Harbin Institute of Technology,University of Electronic Science and Technology of China,Massachusetts Institute of Technology (MIT),Harvard University,Shanghai Zelixir Biotech,CUHK Shenzhen Research Institute
- Organisation type
- Academia,Academia,Academia,Academia,Academia,Academia,Academia,Industry
- Country
- Hong Kong, China, United States of America
- Published
- 8 August 2022
- Authors
- Jiayang Chen, Zhihang Hu, Siqi Sun, Qingxiong Tan, Yixuan Wang, Qinze Yu, Licheng Zong, Liang Hong, Jin Xiao, Tao Shen, Irwin King, Yu Li
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- RNA structure prediction
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
23 million sequences × 1024 tokens per sequence: 23,000,000 × 1,024 = 23 × 10⁶ × 1.024 × 10³ = 2.35 × 10¹⁰ 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
- 2.6 × 10²¹ FLOP
- How it was established
- Hardware
1. Hardware setup: 8x NVIDIA A100 GPUs (3.12E14 FLOP/s per GPU) 2. Training duration: 30 days estimated (2,592,000 seconds) 3. Utilization rate: 40% 4. Calculation: 3.12E14 FLOP/s × 8 GPUs × 2,592,000 seconds × 0.4 = 2.59E21 FLOPs
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
- 8
- Wall-clock time
- 720 hours (30 days)
- Power draw
- 6.4 kW
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
- Hugging Face
- cuhkaih
MIT license https://github.com/ml4bio/RNA-FM Apache 2.0 https://huggingface.co/cuhkaih/rnafm
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
- Citations
- 234
Sources
Where this record came from and when it was last checked.
- Reference
- Interpretable RNA Foundation Model from Unannotated Data for Highly Accurate RNA Structure and Function Predictions
- Last updated
- 25 May 2026
What the numbers mean
About this model
RNA-FM was published by Chinese University of Hong Kong (CUHK),Fudan University,Shanghai AI Lab,Harbin Institute of Technology,University of Electronic Science and Technology of China,Massachusetts Institute of Technology (MIT),Harvard University,Shanghai Zelixir Biotech,CUHK Shenzhen Research Institute, in Hong Kong, in August 2022. The organisation is categorised as academia,Academia,Academia,Academia,Academia,Academia,Academia,Industry.
It works in Biology, and is recorded as doing rNA structure prediction.
The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached. It is published under the cuhkaih organisation on Hugging Face.
How it was trained
Training it took roughly 2.6 × 10²¹ FLOP of computation, on NVIDIA A100 — a measure of what producing the model cost, not of how fast it answers.
Answers
RNA-FM — common questions
Is RNA-FM open source?
Its weights are published, so RNA-FM 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.
How many parameters does RNA-FM have?
No parameter count has been published for RNA-FM, which is why no memory or speed figure appears on this page.
Who created RNA-FM?
RNA-FM was published by Chinese University of Hong Kong (CUHK),Fudan University,Shanghai AI Lab,Harbin Institute of Technology,University of Electronic Science and Technology of China,Massachusetts Institute of Technology (MIT),Harvard University,Shanghai Zelixir Biotech,CUHK Shenzhen Research Institute, based in Hong Kong, categorised as academia,Academia,Academia,Academia,Academia,Academia,Academia,Industry.
When was RNA-FM released?
RNA-FM was published in August 2022. 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 RNA-FM used for?
RNA-FM works in Biology, and is recorded as handling rNA structure prediction. 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.
Where can I download RNA-FM?
Its weights are published under the cuhkaih organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.
How much compute was used to train RNA-FM?
Around 2.6 × 10²¹ FLOP, on 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.
What GPU do I need to run RNA-FM?
We cannot say. RNA-FM 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.
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.