AbGPT

Closed weights Carnegie Mellon University (CMU) 734M parameters 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
Carnegie Mellon University (CMU)
Organisation type
Academia
Country
United States of America
Published
9 September 2024
Authors
Desmond Kuan, Amir Barati Farimani

What it does

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

Domain
Biology
Task
Protein design
Base model
ProtGPT2

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
734M
Training data
6,840,000,000 tokens

Finetuned ProtGPT2 on 57M sequences with average length of ~120 (Figure 6) FT dataset in tokens: 57000000*120=6840000000

Epochs
5

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
4.3 × 10²¹ FLOP

Finetuned ProtGPT2 on 57M sequences with average length of ~120 (Figure 6) FT compute: 734000000*6840000000*5*6=1.506168e+20 Base model compute: 4.1e+21 Total: 4.2506168e+21

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 RTX A6000

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
Closed — provider access only
Model access
Unreleased
Training code
Unreleased

MIT license: https://github.com/deskk/AbGPT

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
AbGPT: De Novo Antibody Design via Generative Language Modeling
Last updated
28 November 2025

What the numbers mean

About this model

AbGPT was published by Carnegie Mellon University (CMU), in United States of America, in September 2024. academia is the category the publisher falls under.

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

It is derived from ProtGPT2 rather than trained from scratch, which is the usual way a specialised model is produced.

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

Training it took roughly 4.3 × 10²¹ FLOP of computation, on NVIDIA RTX A6000 — a measure of what producing the model cost, not of how fast it answers.

It was trained on about 6,840,000,000 tokens of text.

Answers

AbGPT — common questions

01

When was AbGPT released?

AbGPT 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.

02

What is AbGPT used for?

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

03

How much compute was used to train AbGPT?

Around 4.3 × 10²¹ FLOP, on NVIDIA RTX A6000. 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.

04

What GPU do I need to run AbGPT?

None. AbGPT 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 AbGPT open source?

No. AbGPT has not had its weights published, so it exists only as a service controlled by its owner.

06

How many parameters does AbGPT have?

AbGPT has 734M 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.

07

Who created AbGPT?

AbGPT was published by Carnegie Mellon University (CMU), based in United States of America, categorised as academia.

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.