6-layer MLP (MNIST)
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
- Training data
- 60,000 tokens
Table 1
"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
- How it was established
- Operation counting
"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…
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 the country recorded as Switzerland, during March 2010. The category the publisher falls under is academia,Academia,Academia.
It works in the domain of Vision, and is recorded as performing the task of 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 a computation budget of roughly 1.3 × 10¹⁴ FLOP, on hardware recorded as NVIDIA GeForce GTX 280,Intel Core 2 Quad Q9450. That figure measures what producing the model cost, and has no bearing on how fast it answers.
Training consumed a corpus of around 60,000 tokens of text.
Answers
6-layer MLP (MNIST) — common questions
6-layer MLP (MNIST)— is it open source?
The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
6-layer MLP (MNIST)— how many parameters does it have?
It has a parameter count of 12.1M. 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.
6-layer MLP (MNIST)— who created it?
It was published by IDSIA,University of Lugano,SUPSI, based in Switzerland, an organisation categorised as academia,Academia,Academia.
6-layer MLP (MNIST)— when was it released?
It 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.
6-layer MLP (MNIST)— what is it used for?
It works in the domain of Vision, and is recorded as handling the task of character recognition (OCR). These are the areas it was designed around; they describe intent rather than a hard boundary.
6-layer MLP (MNIST)— how much compute was used to train it?
Training consumed around 1.3 × 10¹⁴ FLOP, on hardware recorded as 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.
6-layer MLP (MNIST)— what GPU do I need to run it?
None. This 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.