EquiDock
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
- Massachusetts Institute of Technology (MIT),ETH Zurich,Tencent
- Organisation type
- Academia,Academia,Industry
- Country
- United States of America, Switzerland, China
- Published
- 15 November 2021
- Authors
- Octavian-Eugen Ganea, Xinyuan Huang, Charlotte Bunne, Yatao Bian, Regina Barzilay, Tommi Jaakkola, Andreas Krause
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- 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
- 39,938 tokens
- Epochs
- 30
DIPS Dataset: 39,937 protein pairs Total data points = 39,937 = 3.9937e4
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
- 1.1 × 10¹⁹ FLOP
- How it was established
- Hardware
Training details here: https://docs.nvidia.com/bionemo-framework/latest/models/equidock.html 32 A100s can do 30 epochs per hour on the DIPS dataset. Equidock was trained on 30 epochs on DIPS and 150 epochs on DB5.5. DIPS is about 100x bigger, so the large majority of compute was DIPS. 32 A100-hours = 312 teraflops * 32 * 3600 * 0.3 ~= 1.08e19
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)
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Likely
- Citations
- 171
Sources
Where this record came from and when it was last checked.
- Reference
- Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking
- Last updated
- 25 May 2026
What the numbers mean
Where it came from
EquiDock was published by Massachusetts Institute of Technology (MIT),ETH Zurich,Tencent, in United States of America, in November 2021. The organisation is categorised as academia,Academia,Industry.
It works in Biology, and is recorded as doing proteins.
The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.
How it was trained
Producing it required around 1.1 × 10¹⁹ FLOP of arithmetic, which is a statement about the training budget rather than about inference.
It was trained on about 39,938 tokens of text.
Answers
EquiDock — common questions
Who created EquiDock?
EquiDock was published by Massachusetts Institute of Technology (MIT),ETH Zurich,Tencent, based in United States of America, categorised as academia,Academia,Industry.
When was EquiDock released?
EquiDock was published in November 2021. 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 EquiDock used for?
EquiDock works in Biology, and is recorded as handling proteins. These are the areas it was designed around; they describe intent rather than a hard boundary.
Where can I download EquiDock?
The weights for EquiDock are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
How much compute was used to train EquiDock?
Around 1.1 × 10¹⁹ 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.
What GPU do I need to run EquiDock?
We cannot say. EquiDock 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.
Is EquiDock open source?
Its weights are published, so EquiDock 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 EquiDock have?
No parameter count has been published for EquiDock, which is why no memory or speed figure appears on this page.
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.