AI models
Prithvi-EO-2.0 600M
Training compute
2×10²² FLOP
Parameters
600M
Published
Feb 3, 2025
Prithvi-EO-2.0 600M is an AI model developed by IBM Research, NASA, University of Alabama, University of Iceland, Forschungszentrum Julich, Virginia Tech (Virginia Polytechnic Institute and State University) and 5 more (United States, Iceland and Germany), first published in February 2025. It works in the earth science domain.
Training it took an estimated 2×10²² FLOP of compute (estimation method: hardware). The model has 600,000,000 parameters. Training ran on 240 NVIDIA A100.
Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- IBM Research, NASA, University of Alabama, University of Iceland, Forschungszentrum Julich, Virginia Tech (Virginia Polytechnic Institute and State University), Arizona State University, Oregon State University, Boston University, University of California (UC) Berkeley, Julich Supercomputing Center
- Country of organization
- United States, Iceland, Germany
- Domain
- Earth science
- Training compute
- 2×10²² FLOP
- Compute estimation method
- Hardware
- Parameters
- 600,000,000
- Training hardware
- NVIDIA A100
- Chips used
- 240
- Chip-hours
- 58K
- Training power draw
- 188.5 kW
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Epoch confidence
- Confident
More from IBM Research,NASA,University of Alabama,University of Iceland,Forschungszentrum Julich,Virginia Tech (Virginia Polytechnic Institute and State University),Arizona State University,Oregon State University,Boston University,University of California (UC) Berkeley,Julich Supercomputing Center
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