ProteinSGM

Closed weights University of Toronto February 2023

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 Toronto
Organisation type
Academia
Country
Canada
Published
4 February 2023
Authors
Jin Sub Lee, Jisun Kim, Philip M. Kim

What it does

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

Domain
Biology
Task
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.

Training data
tokens

Total Proteins: 14,987 Training Set = 14,987 × 0.95 = 14,238 Final Estimate = 1.4 × 10^4 datapoints

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 × 10¹⁹ FLOP

"The model is trained with a single NVIDIA V100 GPU using a batch size of 8 and learning rate 1×10−4 for 2 million iterations, which consumes approximately 7 days." Assume FP16 precision and 40% utilization. 1.3e+14*0.4*604800s=3.0e+19

How it was established
Hardware

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 V100
Chips used
1
Wall-clock time
168 hours (7 days)
Power draw
329 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
ProteinSGM: Score-based generative modeling for de novo protein design
Last updated
28 November 2025

What the numbers mean

Background

ProteinSGM was published by University of Toronto, in Canada, in February 2023. It comes out of academia.

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

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

How it was trained

Producing it required around 3 × 10¹⁹ FLOP of arithmetic, on NVIDIA V100, which is a statement about the training budget rather than about inference.

Answers

ProteinSGM — common questions

01

How much compute was used to train ProteinSGM?

Around 3 × 10¹⁹ FLOP, on NVIDIA V100. 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.

02

What GPU do I need to run ProteinSGM?

None. ProteinSGM 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.

03

Is ProteinSGM open source?

The licensing for ProteinSGM was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

04

How many parameters does ProteinSGM have?

No parameter count has been published for ProteinSGM, which is why no memory or speed figure appears on this page.

05

Who created ProteinSGM?

ProteinSGM was published by University of Toronto, based in Canada, categorised as academia.

06

When was ProteinSGM released?

ProteinSGM was published in February 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

07

What is ProteinSGM used for?

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

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.