ShapeMol
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
- Ohio State University
- Country
- United States of America
- Published
- 23 August 2023
- Authors
- Ziqi Chen, Bo Peng, Srinivasan Parthasarathy, Xia Ning
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- 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.
- Parameters
- 2.7M
- Training data
- tokens
1. Training dataset: 1,593,653 molecules
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 × 10¹⁹ FLOP
- How it was established
- Hardware
1. Hardware: 1x Tesla V100 PCIe 32GB (1.30×10¹⁴ FLOP/s) 2. Training duration: directly provided - 140 hours total (80h Shape Encoder + 60h Diffusion Model) = 504,000 seconds 3. Utilization: 40% 4. Calculation: 1.30×10¹⁴ FLOP/s × 1 GPU × 504,000s × 0.4 = 2.60×10¹⁹ 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 V100
- Chips used
- 1
- Wall-clock time
- 140 hours
- Power draw
- 328 W
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
- 18
Sources
Where this record came from and when it was last checked.
- Reference
- Shape-conditioned 3D Molecule Generation via Equivariant Diffusion Models
- Last updated
- 25 May 2026
What the numbers mean
Background
ShapeMol was published by Ohio State University, in United States of America, in August 2023.
It works in Biology, and is recorded as doing drug discovery.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
What went into building it
Producing it required around 2.6 × 10¹⁹ FLOP of arithmetic, on NVIDIA V100, which is a statement about the training budget rather than about inference.
Answers
ShapeMol — common questions
What is ShapeMol used for?
ShapeMol works in Biology, and is recorded as handling drug discovery. These are the areas it was designed around; they describe intent rather than a hard boundary.
How much compute was used to train ShapeMol?
Around 2.6 × 10¹⁹ FLOP, on NVIDIA V100. 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 ShapeMol?
None. ShapeMol 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 ShapeMol open source?
The licensing for ShapeMol 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 ShapeMol have?
ShapeMol has 2.7M parameters. 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.
Who created ShapeMol?
ShapeMol was published by Ohio State University, based in United States of America.
When was ShapeMol released?
ShapeMol was published in August 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.