RNNsearch-50*
No estimate
No hardware requirements for this model
The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- Jacobs University Bremen,University of Montreal / Université de Montréal
- Organisation type
- Academia,Academia
- Country
- Germany, Canada
- Published
- 1 September 2014
- Authors
- D Bahdanau, K Cho, Y Bengio
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Translation
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Training data
- 232,000,000 tokens
[WORDS] "WMT ’14 contains the following English-French parallel corpora: Europarl (61M words), news commentary (5.5M), UN (421M) and two crawled corpora of 90M and 272.5M words respectively, totaling 850M words. Following the procedure described in Cho et al. (2014a), we reduce the size of the combined corpus to have 348M words using the data selection method by Axelrod et al. (2011)."
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- Training compute
- 1.6 × 10¹⁸ FLOP
- How it was established
- Third-party estimation
From https://openai.com/blog/ai-and-compute/ Appendix. 0.018 pfs-days (86400*10^15*0.018) 252 hours in a Quadro K-6000 GPU (assumed utilization: 0.33) 5196000000000 FLOP/s *252 hours * 3600 second/hour * 0.33 utilization = 1555200000000000000 FLOP
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- NVIDIA Quadro K6000
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Frontier model
- Yes
- Why it is tracked
- Highly cited
- Record confidence
- Confident
- Citations
- 29,415
Sources
Where this record came from and when it was last checked.
- Reference
- Neural Machine Translation by Jointly Learning to Align and Translate
- Last updated
- 25 May 2026
What the numbers mean
Background
RNNsearch-50* was published by Jacobs University Bremen,University of Montreal / Université de Montréal, in the country recorded as Germany, during September 2014. It comes out of an organisation categorised as academia,Academia.
It works in the domain of Language, and is recorded as performing the task of translation.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Training and provenance
The training run consumed about 1.6 × 10¹⁸ FLOP, on hardware recorded as NVIDIA Quadro K6000. That figure measures what producing the model cost, and has no bearing on how fast it answers.
Training consumed a corpus of around 232,000,000 tokens of text.
The reason it appears in this catalogue at all: highly cited.
Answers
RNNsearch-50* — common questions
RNNsearch-50*— how many parameters does it have?
No parameter count has been published for it, which is why no memory or speed figure appears on this page.
RNNsearch-50*— who created it?
It was published by Jacobs University Bremen,University of Montreal / Université de Montréal, based in Germany, an organisation categorised as academia,Academia.
RNNsearch-50*— when was it released?
It was published in September 2014. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
RNNsearch-50*— what is it used for?
It works in the domain of Language, and is recorded as handling the task of translation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
RNNsearch-50*— how much compute was used to train it?
Training consumed around 1.6 × 10¹⁸ FLOP, on hardware recorded as NVIDIA Quadro K6000. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.
RNNsearch-50*— what GPU do I need to run it?
None. This is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.
RNNsearch-50*— is it open source?
The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.