BIG LSTM+CNN INPUTS

Closed weights Google Brain 1B parameters February 2016

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 Brain
Organisation type
Industry
Country
United States of America
Published
11 February 2016
Authors
Rafal Jozefowicz, Oriol Vinyals, Mike Schuster, Noam Shazeer, Yonghui Wu

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
1B

1.04B (Table 1)

Training data
tokens

"The experiments are performed on the 1B Word Benchmark data set introduced by (Chelba et al., 2013), which is a publicly available benchmark for measuring progress of statistical language modeling. The data set contains about 0.8B words with a vocabulary of 793471 words, including sentence boundary markers."

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 × 10²⁰ FLOP

assuming (!) 10 days similarly to another model in the paper 240*3600*5046000000000*32*0.3 = 4.1853542e+19 assuming (!) 50 epochs similarly to another model in the paper 6*1.04*10^9*0.8*10^9*50 = 2.496e+20 sqrt(4.1853542e+19*2.496e+20) = 1.0220883e+20

How it was established
Hardware,Operation counting

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 Tesla K40s
Chips used
32
Chip-hours
240
Power draw
16.6 kW
Compute cost
$71

How it is classified

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

Frontier model
Yes
Record confidence
Likely

Sources

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

Reference
Exploring the Limits of Language Modeling
Last updated
28 November 2025

What the numbers mean

What this model is

BIG LSTM+CNN INPUTS was published by Google Brain, in United States of America, in February 2016. It comes out of industry.

It works in Language, and is recorded as doing language modeling.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

How it was trained

Producing it required around 1 × 10²⁰ FLOP of arithmetic, on NVIDIA Tesla K40s, which is a statement about the training budget rather than about inference.

Answers

BIG LSTM+CNN INPUTS — common questions

01

What GPU do I need to run BIG LSTM+CNN INPUTS?

None. BIG LSTM+CNN INPUTS 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.

02

Is BIG LSTM+CNN INPUTS open source?

The licensing for BIG LSTM+CNN INPUTS was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

03

How many parameters does BIG LSTM+CNN INPUTS have?

BIG LSTM+CNN INPUTS has 1B parameters. 1.04B (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.

04

Who created BIG LSTM+CNN INPUTS?

BIG LSTM+CNN INPUTS was published by Google Brain, based in United States of America, categorised as industry.

05

When was BIG LSTM+CNN INPUTS released?

BIG LSTM+CNN INPUTS was published in February 2016. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

06

What is BIG LSTM+CNN INPUTS used for?

BIG LSTM+CNN INPUTS works in Language, and is recorded as handling language modeling. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

07

How much compute was used to train BIG LSTM+CNN INPUTS?

Around 1 × 10²⁰ FLOP, on NVIDIA Tesla K40s. 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.

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.