6-layer MLP (MNIST)

Closed weights IDSIA,University of Lugano,SUPSI 12.1M parameters March 2010

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
IDSIA,University of Lugano,SUPSI
Organisation type
Academia,Academia,Academia
Country
Switzerland
Published
1 March 2010
Authors
Dan Claudiu Ciresan, Ueli Meier, Luca Maria Gambardella, Juergen Schmidhuber

What it does

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

Domain
Vision
Task
Character recognition (OCR)
Numerical format
FP32

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
12.1M

Table 1

Training data
60,000 tokens

"MNIST consists of two datasets, one for training (60,000 images) and one for testing (10,000 images). Many studies divide the training set into two sets consisting of 50,000 images for training and 10,000 for validation. Our network is trained on slightly deformed images, continually generated in on-line fashion; hence we may use the whole un-deformed training set for validation, without wasting training images"

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
1.3 × 10¹⁴ FLOP

"Networks with up to 12 million weights can successfully be trained by plain gradient descent to achieve test errors below 1% after 20-30 epochs in less than 2 hours of training." 60k images in each MNIST epoch. Architecture-based estimate: 6 * 12.11M * 60k * 30 = 1.31e14 We can also get a rough hardware estimate. The authors use single precision, GTX280 gets 6.221e11 FLOPs in single precision. Training 30 epochs takes less than 2 hours, but on each epoch the training set is augmented in onli…

How it was established
Operation counting

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware
NVIDIA GeForce GTX 280,Intel Core 2 Quad Q9450
Wall-clock time
2 hours

"less than 2 hours of training"

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Likely
Citations
1,264

Sources

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

Reference
Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition
Last updated
11 February 2026

What the numbers mean

About this model

6-layer MLP (MNIST) was published by IDSIA,University of Lugano,SUPSI, in Switzerland, in March 2010. academia,Academia,Academia is the category the publisher falls under.

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.

What went into building it

Training it took roughly 1.3 × 10¹⁴ FLOP of computation, on NVIDIA GeForce GTX 280,Intel Core 2 Quad Q9450 — a measure of what producing the model cost, not of how fast it answers.

Around 60,000 tokens went into training it.

Answers

6-layer MLP (MNIST) — common questions

01

Is 6-layer MLP (MNIST) open source?

The licensing for 6-layer MLP (MNIST) was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

02

How many parameters does 6-layer MLP (MNIST) have?

6-layer MLP (MNIST) has 12.1M parameters. Table 1. 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.

03

Who created 6-layer MLP (MNIST)?

6-layer MLP (MNIST) was published by IDSIA,University of Lugano,SUPSI, based in Switzerland, categorised as academia,Academia,Academia.

04

When was 6-layer MLP (MNIST) released?

6-layer MLP (MNIST) was published in March 2010. 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 6-layer MLP (MNIST) used for?

6-layer MLP (MNIST) works in Vision, and is recorded as handling character recognition (OCR). These are the areas it was designed around; they describe intent rather than a hard boundary.

06

How much compute was used to train 6-layer MLP (MNIST)?

Around 1.3 × 10¹⁴ FLOP, on NVIDIA GeForce GTX 280,Intel Core 2 Quad Q9450. 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.

07

What GPU do I need to run 6-layer MLP (MNIST)?

None. 6-layer MLP (MNIST) 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.

Source

Original publication

Record last updated 11 February 2026

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.