DrugFormer

Closed weights University of Florida,University of Texas Health Science Center,H. Lee Moffitt Cancer Center and Research Institute 21.7M parameters August 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 Florida,University of Texas Health Science Center,H. Lee Moffitt Cancer Center and Research Institute
Organisation type
Academia,Academia
Country
United States of America
Published
29 August 2024
Authors
Xiaona Liu, Qing Wang, Minghao Zhou, Yanfei Wang, Xuefeng Wang, Xiaobo Zhou, Qianqian Song

What it does

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

Domain
Biology
Task
Drug Sensitivity 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
21.7M

transformer encoder stack + gated aggregator linear map + classifier + gat = (3*65536+65536+256*1024+1024*256)*6 + 512*256+(2048*256)*32+33+33280

Training data
tokens

How it is classified

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

Record confidence
Likely

Sources

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

Reference
DrugFormer: Graph‐Enhanced Language Model to Predict Drug Sensitivity
Last updated
28 November 2025

What the numbers mean

Where it came from

DrugFormer was published by University of Florida,University of Texas Health Science Center,H. Lee Moffitt Cancer Center and Research Institute, in United States of America, in August 2024. It comes out of academia,Academia.

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

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

Answers

DrugFormer — common questions

01

Who created DrugFormer?

DrugFormer was published by University of Florida,University of Texas Health Science Center,H. Lee Moffitt Cancer Center and Research Institute, based in United States of America, categorised as academia,Academia.

02

When was DrugFormer released?

DrugFormer was published in August 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 DrugFormer used for?

DrugFormer works in Biology, and is recorded as handling drug Sensitivity Prediction. 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 DrugFormer?

None. DrugFormer 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 DrugFormer open source?

The licensing for DrugFormer 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 DrugFormer have?

DrugFormer has 21.7M parameters. transformer encoder stack + gated aggregator linear map + classifier + gat = (3*65536+65536+256*1024+1024*256)*6 + 512*256+(2048*256)*32+33+33280. 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.