RNN for 1B words

Closed weights Google 20B parameters December 2013

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
11 December 2013
Authors
Ciprian Chelba, Tomas Mikolov, Mike Schuster, Qi Ge, Thorsten Brants, Phillipp Koehn, Tony Robinson

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
20B

20B from Table 1

Training data
1,000,000,000 tokens

from abstract: 'With almost one billion words of training data, '

The training run

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

Chips used
24
Chip-hours
5,760
Wall-clock time
240 hours (10 days)

from Table 1,240 hours on 24 CPUs

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Why it is tracked
Highly cited,SOTA improvement

from abstract: 'We show performance of several well-known types of language models, with the best results achieved with a recurrent neural network based language model. The baseline unpruned Kneser-Ney 5-gram model achieves perplexity 67.6; a combination of techniques leads to 35% reduction in perplexity, or 10% reduction in cross-entropy (bits), over that baseline. '

Record confidence
Speculative
Citations
1,205

Sources

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

Reference
One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling
Last updated
28 November 2025

What the numbers mean

What this model is

RNN for 1B words was published by Google, in the country recorded as United States of America, during December 2013. The publishing organisation is categorised as industry.

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 consumed a corpus of around 1,000,000,000 tokens of text.

Its inclusion criterion: highly cited,SOTA improvement.

Answers

RNN for 1B words — common questions

01

RNN for 1B words— 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.

02

RNN for 1B words— 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.

03

RNN for 1B words— 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.

04

RNN for 1B words— how many parameters does it have?

It has a parameter count of 20B. 20B from Table 1. 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.

05

RNN for 1B words— who created it?

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

06

RNN for 1B words— when was it released?

It was published in December 2013. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

Source

Original publication

Record last updated 28 November 2025

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.