PoE 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
- University College London (UCL)
- Organisation type
- Academia
- Country
- United Kingdom of Great Britain and Northern Ireland
- Published
- 28 November 2000
- Authors
- Guy Mayraz, Geoffrey E. Hinton
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
- 3.9M
- Training data
- 54,000 tokens
- Epochs
- 500
10 models, one for each digit. Largest models: 500 epochs, 500 hidden units (Table 2) "The largest network was the best, even though each digit model contains 392,500 parameters trained on only 4,400 images" "the classification network had 30 inputs and therefore 300 weights and 10 output biases." Total: 392500*10 + 310 = 3,925,310
Total training data size is 60000 but the subnetworks were trained on smaller subsets.
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
- 5.2 × 10¹³ FLOP
- How it was established
- Operation counting
Each model was trained on 4400 examples: "The largest network was the best, even though each digit model contains 392,500 parameters trained on only 4,400 images." Table 2, largest network trained 500 epochs. 10 * 6 * 392500 * 4400 * 500 = 51,810,000,000,000
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
- Recognizing Hand-written Digits Using Hierarchical Products of Experts
- Last updated
- 28 November 2025
What the numbers mean
What this model is
PoE MNIST was published by University College London (UCL), in the country recorded as United Kingdom of Great Britain and Northern Ireland, during November 2000. The category the publisher falls under is academia.
It works in the domain of Vision, and is recorded as performing the task of digit recognition.
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 5.2 × 10¹³ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
Training consumed a corpus of around 54,000 tokens of text.
Its inclusion criterion: historical significance.
Answers
PoE MNIST — common questions
PoE 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.
PoE 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.
PoE MNIST— how many parameters does it have?
It has a parameter count of 3.9M. 10 models, one for each digit. Largest models: 500 epochs, 500 hidden units (Table 2) "The largest network was the best, even though each digit model contains 392,500 parameters trained on only 4,400 images" "the classification network had 30 inputs and therefore 300 weights and 10 output biases." Total: 392500*10 + 310 = 3,925,310. 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.
PoE MNIST— who created it?
It was published by University College London (UCL), based in United Kingdom of Great Britain and Northern Ireland, an organisation categorised as academia.
PoE MNIST— when was it released?
It was published in November 2000. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
PoE MNIST— what is it used for?
It works in the domain of Vision, and is recorded as handling the task of digit recognition. 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.
PoE MNIST— how much compute was used to train it?
Training consumed around 5.2 × 10¹³ 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.