DeepRelax

Closed weights National University of Singapore,Sun Yat-sen University,Peking University,China Medical University Hospital,Asia university,Guangdong L-Med Biotechnology Company September 2024

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
National University of Singapore,Sun Yat-sen University,Peking University,China Medical University Hospital,Asia university,Guangdong L-Med Biotechnology Company
Organisation type
Academia,Academia,Academia,Academia,Industry
Country
Singapore, China, Taiwan
Published
17 September 2024
Authors
Ziduo Yang, Yi-Ming Zhao, Xian Wang, Xiaoqing Liu, Xiuying Zhang, Yifan Li, Qiujie Lv, Calvin Yu-Chian Chen & Lei Shen

What it does

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

Domain
Biology
Task
Protein folding 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

"By excluding compounds missing either initial or DFT-relaxed structures, we refined the dataset to 62,724 pairs. " Multiple properties for each structure are predicted in a regression approach.

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
Scalable crystal structure relaxation using an iteration-free deep generative model with uncertainty quantification
Last updated
28 November 2025

What the numbers mean

Background

DeepRelax was published by National University of Singapore,Sun Yat-sen University,Peking University,China Medical University Hospital,Asia university,Guangdong L-Med Biotechnology Company, in Singapore, in September 2024. The organisation is categorised as academia,Academia,Academia,Academia,Industry.

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

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

Answers

DeepRelax — common questions

01

What GPU do I need to run DeepRelax?

None. DeepRelax 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.

02

Is DeepRelax open source?

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

03

How many parameters does DeepRelax have?

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

04

Who created DeepRelax?

DeepRelax was published by National University of Singapore,Sun Yat-sen University,Peking University,China Medical University Hospital,Asia university,Guangdong L-Med Biotechnology Company, based in Singapore, categorised as academia,Academia,Academia,Academia,Industry.

05

When was DeepRelax released?

DeepRelax was published in September 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.

06

What is DeepRelax used for?

DeepRelax works in Biology, and is recorded as handling protein folding 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.

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.