Binarized Neural Network (MNIST)

Closed weights Technion - Israel Institute of Technology,Columbia University,University of Montreal / Université de Montréal 37M parameters March 2016

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
Technion - Israel Institute of Technology,Columbia University,University of Montreal / Université de Montréal
Organisation type
Academia,Academia,Academia
Country
Israel, United States of America, Canada
Published
17 March 2016
Authors
Matthieu Courbariaux, Itay Hubara, Daniel Soudry, Ran El-Yaniv, Yoshua Bengio

What it does

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

Domain
Vision
Task
Image classification

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
37M

Parameter count is not explicitly stated, but they give details: "The MLP we train on MNIST consists of 3 hidden layers of 4096 binary units (see Section 1) and a L2-SVM output layer" Approximately 37m, based on 784 pixels * 4096 + 2 * 4096^2

Training data
60,000 tokens

60k training images, 10k test in MNIST

Epochs
1,000

How it is classified

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

Record confidence
Speculative
Citations
3,299

Sources

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

Reference
Binarized Neural Networks: Training Neural Networks with Weights and Activations Constrained to +1 or −1
Last updated
11 February 2026

What the numbers mean

Where it came from

Binarized Neural Network (MNIST) was published by Technion - Israel Institute of Technology,Columbia University,University of Montreal / Université de Montréal, in the country recorded as Israel, during March 2016. It comes out of an organisation categorised as academia,Academia,Academia.

It works in the domain of Vision, and is recorded as performing the task of image classification.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

Training and provenance

The training set ran to roughly 60,000 tokens of text.

Answers

Binarized Neural Network (MNIST) — common questions

01

Binarized Neural Network (MNIST)— what is it used for?

It works in the domain of Vision, and is recorded as handling the task of image classification. These are the areas it was designed around; they describe intent rather than a hard boundary.

02

Binarized Neural Network (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.

03

Binarized Neural Network (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.

04

Binarized Neural Network (MNIST)— how many parameters does it have?

It has a parameter count of 37M. Parameter count is not explicitly stated, but they give details: "The MLP we train on MNIST consists of 3 hidden layers of 4096 binary units (see Section 1) and a L2-SVM output layer" Approximately 37m, based on 784 pixels * 4096 + 2 * 4096^2. 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.

05

Binarized Neural Network (MNIST)— who created it?

It was published by Technion - Israel Institute of Technology,Columbia University,University of Montreal / Université de Montréal, based in Israel, an organisation categorised as academia,Academia,Academia.

06

Binarized Neural Network (MNIST)— when was it released?

It was published in March 2016. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

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.