MPNNsol

Open weights Ecole Polytechnique F´ed´erale de Lausanne (EPFL),University at Buffalo,University of Washington,Massachusetts Institute of Technology (MIT) June 2024

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
Ecole Polytechnique F´ed´erale de Lausanne (EPFL),University at Buffalo,University of Washington,Massachusetts Institute of Technology (MIT)
Organisation type
Academia,Academia,Academia,Academia
Country
Switzerland, United States of America
Published
19 June 2024
Authors
Casper A. Goverde, Martin Pacesa, Nicolas Goldbach, Lars J. Dornfeld, Petra E. M. Balbi, Sandrine Georgeon, Stéphane Rosset, Srajan Kapoor, Jagrity Choudhury, Justas Dauparas, Christian Schellhaas, Simon Kozlov, David Baker, Sergey Ovchinnikov, Alex J. Vecchio, Bruno E. Correia

What it does

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

Domain
Biology
Task
Protein generation
Base model
ProteinMPNN,AlphaFold 2

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

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
Unreleased

https://github.com/dauparas/ProteinMPNN/tree/main/soluble_model_weights MIT license

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Unknown

Sources

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

Reference
Computational design of soluble and functional membrane protein analogues
Last updated
28 November 2025

What the numbers mean

Background

MPNNsol was published by Ecole Polytechnique F´ed´erale de Lausanne (EPFL),University at Buffalo,University of Washington,Massachusetts Institute of Technology (MIT), in Switzerland, in June 2024. The organisation is categorised as academia,Academia,Academia,Academia.

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

It is derived from ProteinMPNN,AlphaFold 2 rather than trained from scratch, which is the usual way a specialised model is produced.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.

Answers

MPNNsol — common questions

01

Who created MPNNsol?

MPNNsol was published by Ecole Polytechnique F´ed´erale de Lausanne (EPFL),University at Buffalo,University of Washington,Massachusetts Institute of Technology (MIT), based in Switzerland, categorised as academia,Academia,Academia,Academia.

02

When was MPNNsol released?

MPNNsol was published in June 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

03

What is MPNNsol used for?

MPNNsol works in Biology, and is recorded as handling protein generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

04

Where can I download MPNNsol?

The weights for MPNNsol are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

05

What GPU do I need to run MPNNsol?

We cannot say. MPNNsol 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.

06

Is MPNNsol open source?

Its weights are published, so MPNNsol 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.

07

How many parameters does MPNNsol have?

No parameter count has been published for MPNNsol, which is why no memory or speed figure appears on this page.

Source

Original publication

Record last updated 28 November 2025

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.