ConfRank

Closed weights University of Bonn,Institute for Numerical Simulation,Fraunhofer Institute for Algorithms and Scientific Computing 150K parameters November 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 Bonn,Institute for Numerical Simulation,Fraunhofer Institute for Algorithms and Scientific Computing
Organisation type
Academia,Academia
Country
Germany
Published
24 November 2024
Authors
Christian Hölzer, Rick Oerderm, Stefan Grimme, Jan Hamaekers,

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.

Parameters
150K
Training data
1,396,310 tokens

7,349 molecular ensembles × 20 conformers = 146,980 conformers Pairs per ensemble = (20 × 19) ÷ 2 = 190 pairs Total pairs = 7,349 ensembles × 190 pairs = 1,396,310 datapoints

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 GeForce RTX 3070
Chips used
1
Power draw
238 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

Sources

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

Reference
ConfRank: Improving GFN-FF Conformer Ranking with Pairwise Training
Last updated
28 November 2025

What the numbers mean

About this model

ConfRank was published by University of Bonn,Institute for Numerical Simulation,Fraunhofer Institute for Algorithms and Scientific Computing, in Germany, in November 2024. It comes out of academia,Academia.

It works in Biology, and is recorded as doing drug discovery.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

How it was trained

It was trained on about 1,396,310 tokens of text.

Answers

ConfRank — common questions

01

Who created ConfRank?

ConfRank was published by University of Bonn,Institute for Numerical Simulation,Fraunhofer Institute for Algorithms and Scientific Computing, based in Germany, categorised as academia,Academia.

02

When was ConfRank released?

ConfRank was published in November 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 ConfRank used for?

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

04

What GPU do I need to run ConfRank?

None. ConfRank 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 ConfRank open source?

The licensing for ConfRank 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 ConfRank have?

ConfRank has 150K 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.

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.