LCNP 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.
- Published
- 22 November 2009
- Authors
- Rafael Uetz, Sven Behnke
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Object recognition
- Approach
- Supervised
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
- 11.6M
- Training data
- 50,000 tokens
- Epochs
- 1,000
Locally connected: 128*128*4*4*4*5 + 64*64*8*4*4*4 + 32*32*16*4*4*8 + 16*16*32*4*4*16=11534336 Classification head: 16*16*32*10=81920 Total: 11534336+81920=11616256 "five regular layers with the dimensions 256×256, 128×128, . . ., 16×16." "size of the receptive field to be 4 × 4 neurons"
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
- 4.2 × 10¹⁵ FLOP
- How it was established
- Operation counting
2*11616256*3*60000*1000=4181852160000000
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
- Large-scale object recognition with CUDA-accelerated hierarchical neural networks
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
LCNP MNIST was published by its authors, in November 2009.
It works in Vision, and is recorded as doing object recognition.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
How it was trained
The training run consumed about 4.2 × 10¹⁵ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.
Around 50,000 tokens went into training it.
Its inclusion criterion is historical significance.
Answers
LCNP MNIST — common questions
What GPU do I need to run LCNP MNIST?
None. LCNP 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.
Is LCNP MNIST open source?
The licensing for LCNP MNIST 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 LCNP MNIST have?
LCNP MNIST has 11.6M parameters. Locally connected: 128*128*4*4*4*5 + 64*64*8*4*4*4 + 32*32*16*4*4*8 + 16*16*32*4*4*16=11534336 Classification head: 16*16*32*10=81920 Total: 11534336+81920=11616256 "five regular layers with the dimensions 256×256, 128×128, . . ., 16×16." "size of the receptive field to be 4 × 4 neurons". 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.
When was LCNP MNIST released?
LCNP MNIST was published in November 2009. 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 LCNP MNIST used for?
LCNP MNIST works in Vision, and is recorded as handling object recognition. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
How much compute was used to train LCNP MNIST?
Around 4.2 × 10¹⁵ 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.