KinoML
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
- Charité-Universitätsmedizin Berlin,Saarland University,Memorial Sloan Kettering Cancer Center
- Organisation type
- Academia,Academia
- Country
- Germany, United States of America
- Published
- 10 September 2024
- Authors
- Raquel López-Ríos de Castro, Jaime Rodríguez-Guerra, David Schaller, Talia B Kimber, Corey Taylor, Jessica B White, Michael Backenköhler, Alexander Payne, Ben Kaminow, Iván Pulido, Sukrit Singh, Paula Linh Kramer, Guillermo Pérez-Hernández, Andrea Volkamer, John D Chodera
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- Drug discovery, Protein-ligand binding affinity prediction
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
Total Datapoints = KLIFS + KinCo + ChEMBL + PKIS2 = 6,667 + 137,778 + (159,823 + 15,578 + 11,412) + 261,870 = 6,667 + 137,778 + 186,813 + 261,870 = 592,128 ≈ 6.17 × 10⁵
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Closed — provider access only
- Model access
- Unreleased
- Training code
- Open source
MIT license: https://github.com/openkinome/kinoml
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- Lessons learned during the journey of data: from experiment to model for predicting kinase affinity, selectivity, polypharmacology, and resistance
- Last updated
- 28 November 2025
What the numbers mean
About this model
KinoML was published by Charité-Universitätsmedizin Berlin,Saarland University,Memorial Sloan Kettering Cancer Center, in Germany, in September 2024. academia,Academia is the category the publisher falls under.
It works in Biology, and is recorded as doing drug discovery, Protein-ligand binding affinity prediction.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Answers
KinoML — common questions
How many parameters does KinoML have?
No parameter count has been published for KinoML, which is why no memory or speed figure appears on this page.
Who created KinoML?
KinoML was published by Charité-Universitätsmedizin Berlin,Saarland University,Memorial Sloan Kettering Cancer Center, based in Germany, categorised as academia,Academia.
When was KinoML released?
KinoML 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 KinoML used for?
KinoML works in Biology, and is recorded as handling drug discovery, Protein-ligand binding affinity prediction. These are the areas it was designed around; they describe intent rather than a hard boundary.
What GPU do I need to run KinoML?
None. KinoML 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 KinoML open source?
No. KinoML has not had its weights published, so it exists only as a service controlled by its owner.
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.