RAAM

Closed weights 1.5K parameters November 1990

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.

Published
1 November 1990
Authors
Jordan B. Pollack

What it does

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

Domain
Other
Task
Representation learning

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
1.5K

Largest model: "A 48-16-48 RAAM learned to construct representations " Parameters 48*16*2 = 1536

Training data
29 tokens

29 sentence fragments (Figure 10)

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
Confident

Sources

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

Reference
Recursive Distributed Representations
Last updated
28 November 2025

What the numbers mean

Background

RAAM was published by its authors, in November 1990.

It works in Other, and is recorded as doing representation learning.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

How it was trained

It was trained on about 29 tokens of text.

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

Answers

RAAM — common questions

01

What GPU do I need to run RAAM?

None. RAAM 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 RAAM open source?

The licensing for RAAM 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 RAAM have?

RAAM has 1.5K parameters. Largest model: "A 48-16-48 RAAM learned to construct representations " Parameters 48*16*2 = 1536. 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

When was RAAM released?

RAAM was published in November 1990. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

What is RAAM used for?

RAAM works in Other, and is recorded as handling representation learning. These are the areas it was designed around; they describe intent rather than a hard boundary.

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.