SS-pLM

Closed weights Nostrum Biodiscovery,Barcelona Supercomputing Center,Institucio Catalana de Recerca i Estudis Avancçats 14.8M parameters August 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
Nostrum Biodiscovery,Barcelona Supercomputing Center,Institucio Catalana de Recerca i Estudis Avancçats
Organisation type
Government,Research collective
Country
Spain
Published
6 August 2023
Authors
Yaiza Serrano, Sergi Roda, Victor Guallar, Alexis Molina

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
14.8M

From Table 3

Training data
tokens

Total Datapoints = 1.75 × 10⁶ sequences × 300 tokens/sequence = 5.25 × 10⁸ tokens

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
2.3 × 10¹⁹ FLOP

1. Hardware setup: 4x NVIDIA A30 GPUs (1.50×10¹⁴ FLOP/s per GPU in FP16) 2. Training duration: 1 day (86,400 seconds) - directly provided 3. Utilization rate: 40% 4. Calculation: 4 GPUs × 1.50×10¹⁴ FLOP/s × 86,400s × 0.40 = 2.07×10¹⁹ FLOPs 4*1.7e+14*0.4*86400s=2.3e+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 A30 PCIe
Chips used
4
Wall-clock time
24 hours
Power draw
1.3 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
5

Sources

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

Reference
Efficient and accurate sequence generation with small-scale protein language models
Last updated
28 November 2025

What the numbers mean

About this model

SS-pLM was published by Nostrum Biodiscovery,Barcelona Supercomputing Center,Institucio Catalana de Recerca i Estudis Avancçats, in Spain, in August 2023. The organisation is categorised as government,Research collective.

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

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

What went into building it

Producing it required around 2.3 × 10¹⁹ FLOP of arithmetic, on NVIDIA A30 PCIe, which is a statement about the training budget rather than about inference.

Answers

SS-pLM — common questions

01

Who created SS-pLM?

SS-pLM was published by Nostrum Biodiscovery,Barcelona Supercomputing Center,Institucio Catalana de Recerca i Estudis Avancçats, based in Spain, categorised as government,Research collective.

02

When was SS-pLM released?

SS-pLM was published in August 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.

03

What is SS-pLM used for?

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

04

How much compute was used to train SS-pLM?

Around 2.3 × 10¹⁹ FLOP, on NVIDIA A30 PCIe. 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

What GPU do I need to run SS-pLM?

None. SS-pLM 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

Is SS-pLM open source?

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

07

How many parameters does SS-pLM have?

SS-pLM has 14.8M parameters. From Table 3. 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.