IBM Model 4

Closed weights University of Southern California,IBM,University of Pennsylvania July 1999

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
University of Southern California,IBM,University of Pennsylvania
Organisation type
Academia,Industry,Academia
Country
United States of America
Published
2 July 1999
Authors
Yaser Al-Onaizan, Jan Curin, Michael Jahr, Kevin Knight, John Lafferty, Dan Melamed, Franz-Josef Och, David Purdy, Noah A. Smith, and David Yarowsky

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.

Training data
800,000 tokens

[WORDS] See FIgure 6

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,Historical significance
Citations
1,921

Sources

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

Reference
Statistical machine translation
Last updated
28 November 2025

What the numbers mean

What this model is

IBM Model 4 was published by University of Southern California,IBM,University of Pennsylvania, in the country recorded as United States of America, during July 1999. The publishing organisation is categorised as academia,Industry,Academia.

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

Training consumed a corpus of around 800,000 tokens of text.

The reason it appears in this catalogue at all: highly cited,Historical significance.

Answers

IBM Model 4 — common questions

01

IBM Model 4— what is it used for?

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

IBM Model 4— 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

IBM Model 4— 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

IBM Model 4— how many parameters does it have?

No parameter count has been published for it, which is why no memory or speed figure appears on this page.

05

IBM Model 4— who created it?

It was published by University of Southern California,IBM,University of Pennsylvania, based in United States of America, an organisation categorised as academia,Industry,Academia.

06

IBM Model 4— when was it released?

It was published in July 1999. 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.