Project AURIONAI Use-Cases Research & Innovation
IBM
geospatial

Prithvi-EO-2.0 300M

Prithvi-EO-2.0 size variant.

IBMIBMUSANASANASAUSAPrithvi-EO-2.0Family
Figure from the Prithvi-EO-2.0 300M paper: Global HLS dataset distribution visualized on a tile-level.
Levelvariant
Classgeospatial
Parameters300M
Contextnot in the notes
Released3 Dec 2024
Opennessopen source
Runs onsingle datacentre GPU
Statusactive

Industry Use Cases

Public Sector
Satellite monitoring (land cover, floods, forests)

R&D Topics

Earth observation foundation modelsproduced by

Runtimes

TerraTorch

Identity

Developer
IBM, NASA
Family
Prithvi-EO-2.0
Released
3 Dec 2024 sourcesannouncement page
Weights published
–
Record checked
10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
dense transformer ViT masked autoencoder pretrained from scratch on NASA HLS V2, 30 m, about 4.2M samples, 6 bands
Total parameters
300M sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
image
Output
image
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open source
Licence
Apache License 2.0 sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
single datacentre GPU
Footprint
not in the notes
Runtimes
TerraTorch
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Lineage

The notes record no lineage for this model.

Sources

  1. ibm-nasa-geospatial/Prithvi-EO-2.0-600M , Hugging Face huggingface.co https://huggingface.co/ibm-nasa-geospatial/Prithvi-EO-2.0-600M
  2. Leading the way in open Earth observation AI research.ibm.com https://research.ibm.com/blog/earth-observation-leadership
  3. Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications arxiv.org https://arxiv.org/abs/2412.02732v2
  4. github.com/NASA-IMPACT/Prithvi-EO-2.0 https://github.com/NASA-IMPACT/Prithvi-EO-2.0

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Prithvi-EO-2.0 300M", https://aurion.semai.id/models/ibm-prithvi-eo-2-0-300m/, records of October 2026.