Print Recognition Logic

Closed weights IBM January 1963

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
1 January 1963
Authors
L. Kamentsky, Chao-Ning Liu

What it does

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

Domain
Vision
Task
Character recognition (OCR)

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
tokens

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
2.3 × 10⁷ FLOP

0.5*2.5*60*60*5000 = 22500000 = 2.25e7 Assumed utilization of 0.5 Trained for 2-3h on an IBM 7090 (from Introduction) Estimated IBM 7090 at 5000 FLOP/s based on multiplications per second (Nordhaus, 2007) Note: the Nordhaus estimate is very different from Wikipedia's estimate of 100000 FLOP/s, which cites a PowerPoint as source.

How it was established
Hardware

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
3 hours

2-3h (from Introduction)

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
Historical significance
Record confidence
Speculative

Sources

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

Reference
Computer-Automated Design of Multifont Print Recognition Logic
Last updated
28 November 2025

What the numbers mean

What this model is

Print Recognition Logic was published by IBM, in United States of America, in January 1963. It comes out of industry.

It works in Vision, and is recorded as doing character recognition (OCR).

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

How it was trained

The training run consumed about 2.3 × 10⁷ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

It is tracked in the underlying dataset for one reason in particular: historical significance.

Answers

Print Recognition Logic — common questions

01

How much compute was used to train Print Recognition Logic?

Around 2.3 × 10⁷ 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.

02

What GPU do I need to run Print Recognition Logic?

None. Print Recognition Logic 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

Is Print Recognition Logic open source?

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

04

How many parameters does Print Recognition Logic have?

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

05

Who created Print Recognition Logic?

Print Recognition Logic was published by IBM, based in United States of America, categorised as industry.

06

When was Print Recognition Logic released?

Print Recognition Logic was published in January 1963. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

07

What is Print Recognition Logic used for?

Print Recognition Logic works in Vision, and is recorded as handling character recognition (OCR). 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.

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.