MIF-ST

Closed weights Microsoft Research,OpenBioML,University of Chicago October 2022

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
Microsoft Research,OpenBioML,University of Chicago
Organisation type
Industry,Research collective,Academia
Country
United States of America, Multinational
Published
26 October 2022
Authors
Kevin K Yang, Niccolò Zanichelli, Hugh Yeh

What it does

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

Domain
Biology
Task
Proteins, Protein generation

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

42M × 300 = 42,000,000 × 300 = 12,600,000,000 = 1.26e10 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
2.5 × 10²² FLOP

1. Hardware setup: 200x NVIDIA V100 GPUs with 1.30×10^14 FLOP/s per GPU 2. Training duration: Estimated 4 weeks based on "multiple weeks" phrase (4 weeks × 7 days × 24 hours × 3600 seconds = 2,419,200 seconds) 3. Utilization rate: 40% 4. Calculation: 1.30×10^14 FLOP/s × 200 GPUs × 2.4192×10^6 seconds × 0.4 = 2.5×10^22 FLOP

How it was established
Hardware

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
113

Sources

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

Reference
Masked inverse folding with sequence transfer for protein representation learning
Last updated
1 January 2026

What the numbers mean

About this model

MIF-ST was published by Microsoft Research,OpenBioML,University of Chicago, in United States of America, in October 2022. industry,Research collective,Academia is the category the publisher falls under.

It works in Biology, and is recorded as doing proteins, Protein generation.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

Training and provenance

The training run consumed about 2.5 × 10²² FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

Answers

MIF-ST — common questions

01

What is MIF-ST used for?

MIF-ST works in Biology, and is recorded as handling proteins, Protein generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

02

How much compute was used to train MIF-ST?

Around 2.5 × 10²² 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.

03

What GPU do I need to run MIF-ST?

None. MIF-ST 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.

04

Is MIF-ST open source?

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

05

How many parameters does MIF-ST have?

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

06

Who created MIF-ST?

MIF-ST was published by Microsoft Research,OpenBioML,University of Chicago, based in United States of America, categorised as industry,Research collective,Academia.

07

When was MIF-ST released?

MIF-ST was published in October 2022. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

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.