DecompDiff

Closed weights University of Illinois Urbana-Champaign (UIUC),ByteDance,University of Chinese Academy of Sciences,Chinese Academy of Sciences,Tsinghua University February 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
University of Illinois Urbana-Champaign (UIUC),ByteDance,University of Chinese Academy of Sciences,Chinese Academy of Sciences,Tsinghua University
Organisation type
Academia,Industry,Academia,Academia,Academia
Country
United States of America, China
Published
26 February 2024
Authors
Jiaqi Guan, Xiangxin Zhou, Yuwei Yang, Yu Bao, Jian Peng, Jianzhu Ma, Qiang Liu, Liang Wang, Quanquan Gu

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.

Training data
12,500,000 tokens

"100,000 complexes are selected for training" (diffusion based model)

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
1.9 × 10¹⁹ FLOP

1. Hardware setup: 1x NVIDIA A100 GPU (3.12e14 FLOPs/s for FP16) 2. Training duration: 41.7 hours (provided directly) = 150,120 seconds 3. Utilization rate: 40% (assumed) 4. Calculation: 3.12e14 FLOPs/s × 1 GPU × 150,120s × 0.4 = 1.873e19 FLOPs

How it was established
Hardware

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 A100
Chips used
1
Wall-clock time
42 hours
Power draw
435 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
119

Sources

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

Reference
DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design
Last updated
25 May 2026

What the numbers mean

Where it came from

DecompDiff was published by University of Illinois Urbana-Champaign (UIUC),ByteDance,University of Chinese Academy of Sciences,Chinese Academy of Sciences,Tsinghua University, in the country recorded as United States of America, during February 2024. The category the publisher falls under is academia,Industry,Academia,Academia,Academia.

It works in the domain of Biology, and is recorded as performing the task of 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

The training run consumed about 1.9 × 10¹⁹ FLOP, on hardware recorded as NVIDIA A100. That figure measures what producing the model cost, and has no bearing on how fast it answers.

The training set ran to roughly 12,500,000 tokens of text.

Answers

DecompDiff — common questions

01

DecompDiff— what GPU do I need to run it?

None. This 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

DecompDiff— is it open source?

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

03

DecompDiff— how many parameters does it have?

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

04

DecompDiff— who created it?

It was published by University of Illinois Urbana-Champaign (UIUC),ByteDance,University of Chinese Academy of Sciences,Chinese Academy of Sciences,Tsinghua University, based in United States of America, an organisation categorised as academia,Industry,Academia,Academia,Academia.

05

DecompDiff— when was it released?

It was published in February 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

DecompDiff— what is it used for?

It works in the domain of Biology, and is recorded as handling the task of drug discovery. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

07

DecompDiff— how much compute was used to train it?

Training consumed around 1.9 × 10¹⁹ FLOP, on hardware recorded as NVIDIA A100. 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.

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.