AI models
Prithvi-100M
Training compute
2.3×10²¹ FLOP
Parameters
100M
Published
Nov 8, 2023
Prithvi-100M is an AI model developed by IBM and NASA (United States), first published in November 2023. It works in the earth science domain, on tasks such as cloud monitoring / analysis, flood mapping, wildfire mapping and crop mapping / segmentation.
Training it took an estimated 2.3×10²¹ FLOP of compute (estimation method: hardware). The model has 100,000,000 parameters. Training ran on 64 NVIDIA A100.
Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as speculative.
Full record
- Organization
- IBM, NASA
- Country of organization
- United States
- Domain
- Earth science
- Task
- Cloud monitoring / analysis, Flood Mapping, Wildfire Mapping, Crop Mapping / Segmentation
- Training compute
- 2.3×10²¹ FLOP
- Compute estimation method
- Hardware
- Parameters
- 100,000,000
- Training hardware
- NVIDIA A100
- Chips used
- 64
- Training power draw
- 50.8 kW
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- 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