AI models
RNNsearch-50*
Training compute
1.6×10¹⁸ FLOP
Published
Sep 1, 2014
RNNsearch-50* is an AI model developed by Jacobs University Bremen and University of Montreal / Université de Montréal (Germany and Canada), first published in September 2014. It works in the language domain, on tasks such as translation. It counts among the frontier models: the systems trained with the most compute of their moment.
Training it took an estimated 1.6×10¹⁸ FLOP of compute (estimation method: third-party estimation). It was trained on roughly 232M datapoints. Training ran on NVIDIA Quadro K6000.
The reference paper has 29,415 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Jacobs University Bremen, University of Montreal / Université de Montréal
- Country of organization
- Germany, Canada
- Domain
- Language
- Task
- Translation
- Training compute
- 1.6×10¹⁸ FLOP
- Compute estimation method
- Third-party estimation
- Dataset size
- 232M
- Training hardware
- NVIDIA Quadro K6000
- Citations
- 29,415
- 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