IBM-5

Closed weights IBM 1.7M parameters June 1993

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
IBM
Organisation type
Industry
Country
United States of America
Published
15 June 1993
Authors
Peter F. Brown, Stephen A. Della Pietra, Vincent J. Della Pietra, Robert L. Mercer

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.

Parameters
1.7M

The model is initiallized with 2.44E+09 translation probabilities, which are progressively culled until 1,658,364 remain. There are other parameters in the models (eg the fertility probabilities that relate each word in the input to the number of words it will align to) but the parameter count is dominated by the translation probabilities.

Training data
28,850,104 tokens

"They used the algorithm to extract a large number of translations from several years of the proceedings of the Canadian parliament. From these translations, we have chosen as our training data those for which both the English sentence and the French sentence are 30 or fewer words in length. This is a collection of 1,778,620 translations."

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
Citations
5,752

Sources

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

Reference
The Mathematics of Statistical Machine Translation: Parameter Estimation
Last updated
28 November 2025

What the numbers mean

Background

IBM-5 was published by IBM, in United States of America, in June 1993. It comes out of industry.

It works in Language, and is recorded as doing 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

Around 28,850,104 tokens went into training it.

Its inclusion criterion is highly cited.

Answers

IBM-5 — common questions

01

When was IBM-5 released?

IBM-5 was published in June 1993. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

02

What is IBM-5 used for?

IBM-5 works in Language, and is recorded as handling translation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

03

What GPU do I need to run IBM-5?

None. IBM-5 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.

04

Is IBM-5 open source?

The licensing for IBM-5 was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

05

How many parameters does IBM-5 have?

IBM-5 has 1.7M parameters. The model is initiallized with 2.44E+09 translation probabilities, which are progressively culled until 1,658,364 remain. There are other parameters in the models (eg the fertility probabilities that relate each word in the input to the number of words it will align to) but the parameter count is dominated by the translation probabilities. 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.

06

Who created IBM-5?

IBM-5 was published by IBM, based in United States of America, categorised as industry.

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.