LSTM
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
- Technical University of Munich
- Organisation type
- Academia
- Country
- Germany
- Published
- 15 November 1997
- Authors
- Sepp Hochreiter ; Jurgen Schmidhuber
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Language modeling
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.
- Parameters
- 10.5K
- Training data
- 853,000 tokens
Table 2 http://www.bioinf.jku.at/publications/older/2604.pdf
Table 8. The rightmost column lists numbers of training sequences required to achieve the stopping criterion. This applies to experiment 5 (multiplication) Sequences have random lengths, on the order of 100-1000 (table 7 )
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
- 3.2 × 10¹³ FLOP
- How it was established
- Operation counting
"Due to limited computation time, training is stopped after 5 million sequence presentations" Each sequence has p=100 elements in the long-delay setting. COMPUTE = PRESENTATIONS * PRESENTATION LENGTH * UPDATE COMPUTE PER TOKEN 5000000*100*6*10,504.0=
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
- 98,595
Sources
Where this record came from and when it was last checked.
- Reference
- Long short-term memory
- Last updated
- 1 January 2026
What the numbers mean
What this model is
LSTM was published by Technical University of Munich, in the country recorded as Germany, during November 1997. The category the publisher falls under is academia.
It works in the domain of Language, and is recorded as performing the task of language modeling.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
What went into building it
Training it took a computation budget of roughly 3.2 × 10¹³ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
Training consumed a corpus of around 853,000 tokens of text.
Its inclusion criterion: highly cited.
Answers
LSTM — common questions
LSTM— how many parameters does it have?
It has a parameter count of 10.5K. Table 2 http://www.bioinf.jku.at/publications/older/2604.pdf. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.
LSTM— who created it?
It was published by Technical University of Munich, based in Germany, an organisation categorised as academia.
LSTM— when was it released?
It was published in November 1997. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
LSTM— what is it used for?
It works in the domain of Language, and is recorded as handling the task of language modeling. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.
LSTM— how much compute was used to train it?
Training consumed around 3.2 × 10¹³ FLOP. 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.
LSTM— 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.
LSTM— 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.