AI models
pKALM
Parameters
5.1M
Published
Sep 19, 2024
pKALM is an AI model developed by Hokkaido University (Japan), first published in September 2024. It works in the biology domain, on tasks such as protein property prediction.
Epoch AI has no training-compute estimate for this model. The model has 5,083,905 parameters. Training ran on 2 NVIDIA GeForce RTX 3090 Ti.
It is built on top of ESM2-35M. Epoch AI rates the confidence of this record as speculative.
Full record
- Organization
- Hokkaido University
- Country of organization
- Japan
- Domain
- Biology
- Task
- Protein property prediction
- Compute estimation method
- Operation counting
- Parameters
- 5,083,905
- Training hardware
- NVIDIA GeForce RTX 3090 Ti
- Chips used
- 2
- Training power draw
- 1.8 kW
- Base model
- ESM2-35M
- Epoch confidence
- Speculative
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models