AI models
RiNALMo
Training compute
1.1×10²¹ FLOP
Parameters
650M
Published
Feb 29, 2024
RiNALMo is an AI model developed by University of Zagreb, Genome Institute of Singapore and Bioinformatics Institute (Croatia and Singapore), first published in February 2024. It works in the biology domain, on tasks such as rna structure prediction, rna splice-site prediction and mean ribosome load prediction.
Training it took an estimated 1.1×10²¹ FLOP of compute (estimation method: hardware). The model has 650,000,000 parameters. Training ran on 7 NVIDIA A100 for about 336 hours.
The reference paper has 108 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- University of Zagreb, Genome Institute of Singapore, Bioinformatics Institute
- Country of organization
- Croatia, Singapore
- Domain
- Biology
- Task
- RNA structure prediction, RNA splice-site prediction, Mean ribosome load prediction
- Training compute
- 1.1×10²¹ FLOP
- Compute estimation method
- Hardware
- Parameters
- 650,000,000
- Training hardware
- NVIDIA A100
- Chips used
- 7
- Training time
- 336 h
- Training power draw
- 5.5 kW
- Citations
- 108
- 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