LeNet-5
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
- 1 November 1998
- Authors
- Yann LeCun, Léon Bottou, Yoshua Bengio, Patrick Haffner
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.
- Parameters
- 60K
- Training data
- 60,000 tokens
"[LeNet5] contains 390408 connections, but only 60000 trainable free parameters because of the weight sharing"
The MNIST database contains 60,000 training images and 10,000 testing images (Wikipedia)
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
- 2.8 × 10¹² FLOP
- How it was established
- Operation counting
"[LeNet5] contains 390408 connections" = multiply-adds MNIST - 60,000 data points 20 epochs 390408*60000*6*20=2.810938e+12
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,Highly cited
- Record confidence
- Confident
- Citations
- 57,900
Sources
Where this record came from and when it was last checked.
- Reference
- Gradient-based Learning Applied to Document Recognition
- Last updated
- 1 January 2026
What the numbers mean
About this model
LeNet-5 was published by AT&T, in United States of America, in November 1998. The organisation is categorised as industry.
It works in Vision, and is recorded as doing character recognition (OCR).
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
What went into building it
The training run consumed about 2.8 × 10¹² FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.
Around 60,000 tokens went into training it.
Its inclusion criterion is historical significance,Highly cited.
Answers
LeNet-5 — common questions
Is LeNet-5 open source?
The licensing for LeNet-5 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 LeNet-5 have?
LeNet-5 has 60K parameters. "[LeNet5] contains 390408 connections, but only 60000 trainable free parameters because of the weight sharing". 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 LeNet-5?
LeNet-5 was published by AT&T, based in United States of America, categorised as industry.
When was LeNet-5 released?
LeNet-5 was published in November 1998. 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 LeNet-5 used for?
LeNet-5 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.
How much compute was used to train LeNet-5?
Around 2.8 × 10¹² 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.
What GPU do I need to run LeNet-5?
None. LeNet-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.
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.