METL-Global

Closed weights University of Wisconsin Madison,Morgridge Institute for Research 50M parameters April 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 Wisconsin Madison,Morgridge Institute for Research
Organisation type
Academia,Academia
Country
United States of America
Published
17 April 2024
Authors
Sam Gelman, Bryce Johnson, Chase Freschlin, Sameer D’Costa, Anthony Gitter, Philip A. Romero

What it does

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

Domain
Biology
Task
Protein or nucleotide language model (pLM/nLM), Protein design

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
50M
Training data
tokens

New estimate, Global only: 30M * 200 residues = 6000000000 Combined data 50M variants (20M + 30M) × 200 residues = 10 billion (1.0e10) tokens 20M from METL-Local 30M from METL-Global (148 proteins × 200k variants) Average sequence length: 200 residues Final estimate: 1.0e10 tokens

Epochs
30

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Chips used
4

How it is classified

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

Record confidence
Likely
Citations
25

Sources

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

Reference
Biophysics-based protein language models for protein engineering
Last updated
1 January 2026

What the numbers mean

About this model

METL-Global was published by University of Wisconsin Madison,Morgridge Institute for Research, in United States of America, in April 2024. academia,Academia is the category the publisher falls under.

It works in Biology, and is recorded as doing protein or nucleotide language model (pLM/nLM), Protein design.

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

Answers

METL-Global — common questions

01

What GPU do I need to run METL-Global?

None. METL-Global 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 METL-Global open source?

The licensing for METL-Global 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 METL-Global have?

METL-Global has 50M 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.

04

Who created METL-Global?

METL-Global was published by University of Wisconsin Madison,Morgridge Institute for Research, based in United States of America, categorised as academia,Academia.

05

When was METL-Global released?

METL-Global was published in April 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 METL-Global used for?

METL-Global works in Biology, and is recorded as handling protein or nucleotide language model (pLM/nLM), Protein design. 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 1 January 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.