pKALM
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
- Hokkaido University
- Organisation type
- Academia
- Country
- Japan
- Published
- 19 September 2024
- Authors
- Shijie Xu, Akira Onoda
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- Protein property prediction
- Base model
- ESM2-35M
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
- 5.1M
- Training data
- tokens
- Epochs
- 130
Loaded checkpoint and counted parameters.
Two datasets were used: "The revised data set now includes 1,450 pKa values for 165 wild-type proteins and 262 pKa values for 47 mutant proteins." "These data sets, derived from references containing experimen- tal pI values, comprise 119,092 peptide pI values and 2,324 protein pI values." Total assuming avg 300 tokens per example: (1450+165+262+47+119092+2324)*300=37002000
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
- Operation counting
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 GeForce RTX 3090 Ti
- Chips used
- 2
- Power draw
- 1.8 kW
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Speculative
Sources
Where this record came from and when it was last checked.
- Reference
- Accurate and Rapid Prediction of Protein pKa: Protein Language Models Reveal the Sequence-pKa Relationship
- Last updated
- 28 November 2025
What the numbers mean
About this model
pKALM was published by Hokkaido University, in Japan, in September 2024. It comes out of academia.
It works in Biology, and is recorded as doing protein property prediction.
It builds on ESM2-35M, which is why it shares that model's general shape and size.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
Answers
pKALM — common questions
Who created pKALM?
pKALM was published by Hokkaido University, based in Japan, categorised as academia.
When was pKALM released?
pKALM was published in September 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 pKALM used for?
pKALM works in Biology, and is recorded as handling protein property prediction. These are the areas it was designed around; they describe intent rather than a hard boundary.
What GPU do I need to run pKALM?
None. pKALM 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 pKALM open source?
The licensing for pKALM 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 pKALM have?
pKALM has 5.1M parameters. Loaded checkpoint and counted 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.