AI models
Novae
Training compute
1.1×10¹⁹ FLOP
Parameters
32M
Published
Sep 13, 2024
Novae is an AI model developed by CentraleSupelec, Gustave Roussy and Université Paris Cité (France), first published in September 2024. It works in the biology domain, on tasks such as spatial transcriptomics.
Training it took an estimated 1.1×10¹⁹ FLOP of compute (estimation method: hardware). The model has 32,000,000 parameters. Training ran on 1 NVIDIA A100 SXM4 40 GB for about 24 hours.
Access: Open weights (non-commercial). Its weights are openly available. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- CentraleSupelec, Gustave Roussy, Université Paris Cité
- Country of organization
- France
- Domain
- Biology
- Task
- Spatial Transcriptomics
- Training compute
- 1.1×10¹⁹ FLOP
- Compute estimation method
- Hardware
- Parameters
- 32,000,000
- Training hardware
- NVIDIA A100 SXM4 40 GB
- Chips used
- 1
- Training time
- 24 h
- Training power draw
- 433 W
- Model accessibility
- Open weights (non-commercial)
- Open weights
- Yes
- Epoch confidence
- Confident
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