Word2Vec (large)

Closed weights Google 692M parameters October 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
16 October 2013
Authors
T Mikolov, I Sutskever, K Chen, GS Corrado

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Language
Task
Semantic embedding

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
692M

We discarded from the vocabulary all words that occurred less than 5 times in the training data, which resulted in a vocabulary of size 692K

Training data
330,000,000,000 tokens

"we increased the amount of the training data by using a dataset with about 33 billion words"

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
3.9 × 10¹⁶ FLOP

From https://openai.com/blog/ai-and-compute/ Appendix. "less than 0.00045 pfs days" (86400*10^15*0.00045)

How it was established
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
24 hours

Table 5 appears to call the model "Skip-Phrase" and says it took 1 day

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
Record confidence
Likely
Citations
35,201

Sources

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

Reference
Distributed Representations of Words and Phrases and their Compositionality
Last updated
25 May 2026

What the numbers mean

About this model

Word2Vec (large) was published by Google, in United States of America, in October 2013. The organisation is categorised as industry.

It works in Language, and is recorded as doing semantic embedding.

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

Training and provenance

Producing it required around 3.9 × 10¹⁶ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

Around 330,000,000,000 tokens went into training it.

It is tracked in the underlying dataset for one reason in particular: highly cited.

Answers

Word2Vec (large) — common questions

01

What GPU do I need to run Word2Vec (large)?

None. Word2Vec (large) 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 Word2Vec (large) open source?

The licensing for Word2Vec (large) 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 Word2Vec (large) have?

Word2Vec (large) has 692M parameters. We discarded from the vocabulary all words that occurred less than 5 times in the training data, which resulted in a vocabulary of size 692K. 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 Word2Vec (large)?

Word2Vec (large) was published by Google, based in United States of America, categorised as industry.

05

When was Word2Vec (large) released?

Word2Vec (large) was published in October 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.

06

What is Word2Vec (large) used for?

Word2Vec (large) works in Language, and is recorded as handling semantic embedding. 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 Word2Vec (large)?

Around 3.9 × 10¹⁶ 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 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.