SNM-skip

Closed weights Google 62B parameters December 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
3 December 2014
Authors
Noam Shazeer, Joris Pelemans, Ciprian Chelba

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
62B

62B from Table 2

Training data
800,000,000 tokens

1B from 'Our experimental setup used the One Billion Word Benchmark corpus' from section 4.1 - 'Total number of training tokens is about 0.8 billion'

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 × 10²⁰ FLOP

https://www.wolframalpha.com/input?i=0.8+billion+*+62+billion+*+6+FLOP

How it was established
Operation counting

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
SOTA improvement

'When using skip-gram features the models are able to match the state-of-the-art recurrent neural network (RNN) LMs; combining the two modeling techniques yields the best known result on the benchmark. ' - from abstract

Record confidence
Speculative
Citations
14

Sources

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

Reference
Skip-gram Language Modeling Using Sparse Non-negative Matrix Probability Estimation
Last updated
28 November 2025

What the numbers mean

Background

SNM-skip was published by Google, in the country recorded as United States of America, during December 2014. It comes out of an organisation categorised as industry.

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

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

Training and provenance

Producing it required arithmetic totalling around 3 × 10²⁰ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

The training set ran to roughly 800,000,000 tokens of text.

It is tracked in the underlying dataset for one reason in particular: sOTA improvement.

Answers

SNM-skip — common questions

01

SNM-skip— 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.

02

SNM-skip— 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.

03

SNM-skip— how many parameters does it have?

It has a parameter count of 62B. 62B from Table 2. 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

SNM-skip— who created it?

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

05

SNM-skip— when was it released?

It was published in December 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.

06

SNM-skip— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

07

SNM-skip— how much compute was used to train it?

Training consumed around 3 × 10²⁰ 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.

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.