ProCALM (Uniref9B)
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
- Profluent Bio,California Institute of Technology
- Organisation type
- Industry,Academia
- Country
- United States of America
- Published
- 9 October 2024
- Authors
- Jason Yang, Aadyot Bhatnagar, Jeffrey A. Ruffolo, Ali Madani
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- Proteins, Protein generation
- Base model
- ProGen2-base
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
- 764M
- Training data
- tokens
"We trained two different ProCALM models – one on 9 billion tokens of enzyme sequences from Uniref, and one on 1.5 billion tokens of enzyme sequences from Swissprot Train"
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.
- How it was established
- Hardware
- Fine-tuning compute
- 8.1 × 10¹⁹ FLOP
"Impressively, our Uniref9B and Swissprot-1.5B models only required 240 and 40 A100-hours to train, respectively" 240/4=60h across 4 A100 Finetuning compute: 240*60*60*312000000000000*0.3=8.08704e+19
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
- Chips used
- 4
- Wall-clock time
- 60 hours
- Power draw
- 3.2 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
- 9
Sources
Where this record came from and when it was last checked.
- Reference
- Conditional Enzyme Generation Using Protein Language Models with Adapters
- Last updated
- 25 May 2026
What the numbers mean
What this model is
ProCALM (Uniref9B) was published by Profluent Bio,California Institute of Technology, in United States of America, in October 2024. The organisation is categorised as industry,Academia.
It works in Biology, and is recorded as doing proteins, Protein generation.
Its starting point was ProGen2-base — most models at this scale are adapted from an existing base rather than built from nothing.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
Answers
ProCALM (Uniref9B) — common questions
Who created ProCALM (Uniref9B)?
ProCALM (Uniref9B) was published by Profluent Bio,California Institute of Technology, based in United States of America, categorised as industry,Academia.
When was ProCALM (Uniref9B) released?
ProCALM (Uniref9B) was published in October 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.
What is ProCALM (Uniref9B) used for?
ProCALM (Uniref9B) 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.
What GPU do I need to run ProCALM (Uniref9B)?
None. ProCALM (Uniref9B) 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.
Is ProCALM (Uniref9B) open source?
The licensing for ProCALM (Uniref9B) was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
How many parameters does ProCALM (Uniref9B) have?
ProCALM (Uniref9B) has 764M parameters. 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.
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.