ProGen

Closed weights Salesforce Research,Stanford University 1.2B parameters March 2020

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
Salesforce Research,Stanford University
Organisation type
Industry,Academia
Country
United States of America
Published
13 March 2020
Authors
Ali Madani, Bryan McCann, Nikhil Naik, Nitish Shirish Keskar, Namrata Anand, Raphael R. Eguchi, View ORCID ProfilePo-Ssu Huang, Richard Socher

What it does

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

Domain
Biology
Task
Protein generation, Proteins, Protein or nucleotide language model (pLM/nLM)
Approach
Self-supervised learning

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
1.2B

"We train a 1.2B-parameter language model, ProGen, on ∼280M protein sequences"

Training data
tokens

1,049B from Table 9 https://www.biorxiv.org/content/10.1101/2023.07.05.547496v1

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
3.7 × 10²⁰ FLOP

Our model was implemented in TensorFlow (Abadi et al., 2016) and trained with a global batch size of 64 distributed across 256 cores of a Cloud TPU v3 Pod for 1M iterations. Training took approximately two weeks using Adagrad (Duchi et al., 2011) 4.00E+12*256*60**2*24*14*0.3 = 3.7e20 7.6E+21 FLOPs from Table 9 https://www.biorxiv.org/content/10.1101/2023.07.05.547496v1

How it was established
Hardware,Third-party estimation

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
315

Sources

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

Reference
ProGen: Language Modeling for Protein Generation
Last updated
1 January 2026

What the numbers mean

What this model is

ProGen was published by Salesforce Research,Stanford University, in United States of America, in March 2020. The organisation is categorised as industry,Academia.

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

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

Training and provenance

Training it took roughly 3.7 × 10²⁰ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.

Answers

ProGen — common questions

01

When was ProGen released?

ProGen was published in March 2020. 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 ProGen used for?

ProGen works in Biology, and is recorded as handling protein generation, Proteins, Protein or nucleotide language model (pLM/nLM). 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.

03

How much compute was used to train ProGen?

Around 3.7 × 10²⁰ FLOP. 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 ProGen?

None. ProGen 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 ProGen open source?

The licensing for ProGen 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 ProGen have?

ProGen has 1.2B parameters. "We train a 1.2B-parameter language model, ProGen, on ∼280M protein sequences". 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 ProGen?

ProGen was published by Salesforce Research,Stanford University, based in United States of America, categorised as industry,Academia.

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.