Profile Prediction

Closed weights University of Washington,Salesforce Research December 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
University of Washington,Salesforce Research
Organisation type
Academia,Industry
Country
United States of America
Published
1 December 2020
Authors
Pascal Sturmfels, Jesse Vig, Ali Madani, Nazneen Fatema Rajani

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), Proteins

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

32 million sequences × 250 residues/sequence = 8 billion data points [32 × 10^6 × 250 = 8 × 10^9]

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
5 × 10²⁰ FLOP

1. Hardware setup: 8x NVIDIA Tesla V100 GPUs (130 TFLOP/s each) 2. Training duration: 2 weeks (1.2e+6 seconds) - directly provided 3. Utilization rate: 40% 4. Final calculation: 8 GPUs × 1.30e+14 FLOP/s × 1.2e+6 seconds × 0.4 utilization = 5.0e+20 FLOPs

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
8
Power draw
4.9 kW

How it is classified

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

Record confidence
Confident
Citations
27

Sources

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

Reference
Profile Prediction: An Alignment-Based Pre-Training Task for Protein Sequence Models
Last updated
25 May 2026

What the numbers mean

Background

Profile Prediction was published by University of Washington,Salesforce Research, in United States of America, in December 2020. academia,Industry is the category the publisher falls under.

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

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 5 × 10²⁰ FLOP of computation, on NVIDIA V100 — a measure of what producing the model cost, not of how fast it answers.

Answers

Profile Prediction — common questions

01

When was Profile Prediction released?

Profile Prediction was published in December 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 Profile Prediction used for?

Profile Prediction works in Biology, and is recorded as handling protein or nucleotide language model (pLM/nLM), Proteins. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

03

How much compute was used to train Profile Prediction?

Around 5 × 10²⁰ 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.

04

What GPU do I need to run Profile Prediction?

None. Profile Prediction 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 Profile Prediction open source?

The licensing for Profile Prediction 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 Profile Prediction have?

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

07

Who created Profile Prediction?

Profile Prediction was published by University of Washington,Salesforce Research, based in United States of America, categorised as academia,Industry.

Source

Original publication

Record last updated 25 May 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.