Handwritten digit recognition network
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
- AT&T
- Organisation type
- Industry
- Country
- United States of America
- Published
- 27 November 1989
- Authors
- Yann LeCun, B. Boser, J. Denker, D. Henderson, R. Howard, W. Hubbard, L. Jackel
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Digit recognition
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
- 2.6K
- Training data
- 9,840 tokens
- Epochs
- 30
"In summary, the network has 4635 units, 98442 connections, and 2578 independent parameters.“
"After 30 training passes the error rate on training set (7291 handwritten plus 2549 printed digits)"
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
- 1.8 × 10¹¹ FLOP
- How it was established
- Hardware
1.4e6 * 3 * 24 * 60* 60 * 0.5 = 181440000000 = 1.81e11 "A complete training session (30 passes through the training set plus test) takes about 3 days on a SUN SPARCstation 1" Sparcstation 1 has an estimated compute of 1.4 MFLOPS (source: https://ieeexplore.ieee.org/document/63671 )
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
- 72 hours
"A complete training session (30 passes through the training set plus test) takes about 3 days on a SUN SPARCstation 1"
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
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- Handwritten Digit Recognition with a Back-Propagation Network
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
Handwritten digit recognition network was published by AT&T, in United States of America, in November 1989. The organisation is categorised as industry.
It works in Vision, and is recorded as doing digit recognition.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
Training and provenance
The training run consumed about 1.8 × 10¹¹ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.
It was trained on about 9,840 tokens of text.
The reason it appears in this catalogue at all is historical significance.
Answers
Handwritten digit recognition network — common questions
What GPU do I need to run Handwritten digit recognition network?
None. Handwritten digit recognition network 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.
Is Handwritten digit recognition network open source?
The licensing for Handwritten digit recognition network was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
How many parameters does Handwritten digit recognition network have?
Handwritten digit recognition network has 2.6K parameters. "In summary, the network has 4635 units, 98442 connections, and 2578 independent parameters.“. 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.
Who created Handwritten digit recognition network?
Handwritten digit recognition network was published by AT&T, based in United States of America, categorised as industry.
When was Handwritten digit recognition network released?
Handwritten digit recognition network was published in November 1989. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is Handwritten digit recognition network used for?
Handwritten digit recognition network works in Vision, and is recorded as handling digit recognition. These are the areas it was designed around; they describe intent rather than a hard boundary.
How much compute was used to train Handwritten digit recognition network?
Around 1.8 × 10¹¹ 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.
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.