LBSTER

Closed weights Prescient Design,Genentech 67M parameters May 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
Prescient Design,Genentech
Organisation type
Industry,Industry
Country
United States of America
Published
15 May 2024
Authors
Nathan C. Frey, Taylor Joren, Aya Abdelsalam Ismail, Allen Goodman, Richard Bonneau, Kyunghyun Cho, Vladimir Gligorijević

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)

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
67M

"we are able to train a 67 million parameter model"

Training data
3,375,000,000 tokens

UniRef50 dataset size calculation: 43,000,000 sequences × 300 tokens/sequence = 1.29 × 10¹⁰ tokens Training process calculation: 1,048,576 tokens/step × 50,000 steps = 5.24288 × 10¹⁰ total tokens Epochs calculation: 5.24288 × 10¹⁰ / 1.29 × 10¹⁰ = 4.06 epochs Final unique tokens (first epoch only): 1.3 × 10¹⁰ tokens

Epochs
4.06

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
1.1 × 10¹⁹ FLOP

1 day on 1 A100 312000000000000*1day*0.4=10782720000000000000

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 A100 SXM4 80 GB
Chips used
1
Wall-clock time
24 hours

"we are able to train a 67 million parameter model in a single day

Power draw
434 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
Citations
4

Sources

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

Reference
Cramming Protein Language Model Training in 24 GPU Hours
Last updated
28 November 2025

What the numbers mean

What this model is

LBSTER was published by Prescient Design,Genentech, in the country recorded as United States of America, during May 2024. It comes out of an organisation categorised as industry,Industry.

It works in the domain of Biology, and is recorded as performing the task of protein or nucleotide language model (pLM/nLM).

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

How it was trained

Training it took a computation budget of roughly 1.1 × 10¹⁹ FLOP, on hardware recorded as NVIDIA A100 SXM4 80 GB. That figure measures what producing the model cost, and has no bearing on how fast it answers.

The training set ran to roughly 3,375,000,000 tokens of text.

Answers

LBSTER — common questions

01

LBSTER— who created it?

It was published by Prescient Design,Genentech, based in United States of America, an organisation categorised as industry,Industry.

02

LBSTER— when was it released?

It was published in May 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.

03

LBSTER— what is it used for?

It works in the domain of Biology, and is recorded as handling the task of protein or nucleotide language model (pLM/nLM). These are the areas it was designed around; they describe intent rather than a hard boundary.

04

LBSTER— how much compute was used to train it?

Training consumed around 1.1 × 10¹⁹ FLOP, on hardware recorded as NVIDIA A100 SXM4 80 GB. 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.

05

LBSTER— what GPU do I need to run it?

None. This 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.

06

LBSTER— is it open source?

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

07

LBSTER— how many parameters does it have?

It has a parameter count of 67M. "we are able to train a 67 million parameter model". 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.

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.