DiffDock-PP

Closed weights Technical University of Munich,Massachusetts Institute of Technology (MIT) 1.6M parameters April 2023

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
Technical University of Munich,Massachusetts Institute of Technology (MIT)
Organisation type
Academia,Academia
Country
Germany, United States of America
Published
8 April 2023
Authors
Mohamed Amine Ketata, Cedrik Laue, Ruslan Mammadov, Hannes Stärk, Menghua Wu, Gabriele Corso, Céline Marquet, Regina Barzilay, Tommi S. Jaakkola

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Biology
Task
Protein interaction 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.

Parameters
1.6M
Training data
42,826 tokens

42,826 pairs approximated at 500 tokens 42826*500=21413000

Epochs
170

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
3.5 × 10¹⁶ FLOP

Using 6ND formula with 170 epochs 6*21413000*1620000*170=3.5382841e+16

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
67

Sources

Where this record came from and when it was last checked.

Reference
DiffDock-PP: Rigid Protein-Protein Docking with Diffusion Models
Last updated
25 May 2026

What the numbers mean

About this model

DiffDock-PP was published by Technical University of Munich,Massachusetts Institute of Technology (MIT), in Germany, in April 2023. academia,Academia is the category the publisher falls under.

It works in Biology, and is recorded as doing protein interaction prediction.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

What went into building it

Producing it required around 3.5 × 10¹⁶ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

The training set ran to roughly 42,826 tokens.

Answers

DiffDock-PP — common questions

01

When was DiffDock-PP released?

DiffDock-PP was published in April 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.

02

What is DiffDock-PP used for?

DiffDock-PP works in Biology, and is recorded as handling protein interaction 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.

03

How much compute was used to train DiffDock-PP?

Around 3.5 × 10¹⁶ 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.

04

What GPU do I need to run DiffDock-PP?

None. DiffDock-PP 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.

05

Is DiffDock-PP open source?

The licensing for DiffDock-PP was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

06

How many parameters does DiffDock-PP have?

DiffDock-PP has 1.6M 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.

07

Who created DiffDock-PP?

DiffDock-PP was published by Technical University of Munich,Massachusetts Institute of Technology (MIT), based in Germany, categorised as academia,Academia.

Source

Original publication

Record last updated 25 May 2026

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.