Seq2Seq LSTM

Closed weights Google 1.9B parameters September 2014

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
Google
Organisation type
Industry
Country
United States of America
Published
10 September 2014
Authors
Ilya Sutskever, Oriol Vinyals, Quoc V. Le

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.

Parameters
1.9B

The resulting LSTM has 384M parameters of which 64M are pure recurrent connections (32M for the “encoder” LSTM and 32M for the “decoder” LSTM). The paper uses an ensemble of 5 LSTMs.

Training data
870,000,000 tokens

[WORDS] "We used the WMT’14 English to French dataset. We trained our models on a subset of 12M sentences consisting of 348M French words and 304M English words, which is a clean “selected” subset from [29]."

Epochs
7.5

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
5.6 × 10¹⁹ FLOP

384E+6 parameters * 2 FLOP/parameter * (348E+6 + 304E+6 points per epoch) * 7.5 epochs * 3 FLOP/point ~= 1.126656e+19 FLOP Times 5 independent models in ensemble => 5.6E+19 FLOP If we assume NVIDIA K40 (in use at the time): 10 days * 24 * 60 * 60 seconds/day * 8 GPUs * 33% * 5e12 FLOP/s * 5 models in ensemble ~= 5.7E+19 FLOP Authors of "AI and Memory Wall" estimated model's training compute as 11,000 PFLOPS = 1.1*10^19 FLOPS (https://github.com/amirgholami/ai_and_memory_wall)

How it was established
Operation counting,Hardware,Third-party estimation

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Wall-clock time
240 hours (10 days)

Training took about 10 days

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
22,025

Sources

Where this record came from and when it was last checked.

Reference
Sequence to Sequence Learning with Neural Networks
Last updated
25 May 2026

What the numbers mean

Where it came from

Seq2Seq LSTM was published by Google, in the country recorded as United States of America, during September 2014. The category the publisher falls under is industry.

It works in the domain of Language, and is recorded as performing the task of translation.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

What went into building it

Producing it required arithmetic totalling around 5.6 × 10¹⁹ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

The training set ran to roughly 870,000,000 tokens of text.

Its inclusion criterion: highly cited.

Answers

Seq2Seq LSTM — common questions

01

Seq2Seq 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.

02

Seq2Seq LSTM— how many parameters does it have?

It has a parameter count of 1.9B. The resulting LSTM has 384M parameters of which 64M are pure recurrent connections (32M for the “encoder” LSTM and 32M for the “decoder” LSTM). The paper uses an ensemble of 5 LSTMs. 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.

03

Seq2Seq LSTM— who created it?

It was published by Google, based in United States of America, an organisation categorised as industry.

04

Seq2Seq LSTM— 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.

05

Seq2Seq LSTM— 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.

06

Seq2Seq LSTM— how much compute was used to train it?

Training consumed around 5.6 × 10¹⁹ 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.

07

Seq2Seq 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.

Source

Original publication

Record last updated 25 May 2026

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.