Skip to content
ModelListedExternal
Download

Mnist 4.5k

This is an ultra-lightweight Convolutional Neural Network (CNN) with only 4.5K parameters, trained on the classic MNIST dataset for handwritten digit recognition.

Sourcehuggingface.co/aplominski/mnist-4.5k/tree/1d0df2a6e690d6843e6891c1f0716d72df4c2d1c
KindOtherVersionRevision 1d0df2aCgrade

Model source

Kind
Other
File size
20.6 KB
Version
vRevision 1d0df2a
Updated
Nov 2, 2026
Downloads
0
Source
Hugging Face

Source description

Lightweight MNIST CNN (4.5K Parameters)

This is an ultra-lightweight Convolutional Neural Network (CNN) with only 4.5K parameters, trained on the classic MNIST dataset for handwritten digit recognition.

Despite its minimal size, the model achieves 94.48% accuracy on the test split, making it highly efficient for edge devices or CPU-only environments.

The full training workflow and source code can be found on GitHub and weights can be found on Hugging Face

Model Performance

  • Task: Image Classification (Handwritten Digits 0-9)
  • Dataset: MNIST
  • Test Accuracy: 94.48%
  • Parameter Count: ~4,500

Quick Start / Usage

You can load and use this model directly using the code in github repository

Sources

1 source
Hugging FacePrimaryVersion 1d0df2a6e690d6843e6891c1f0716d72df4c2d1c
huggingface.co/aplominski/mnist-4.5k/tree/1d0df2a6e690d6843e6891c1f0716d72df4c2d1c

Verified Nov 2

Download files

Repository files

File inventory only; completeness is unverified.

Model artifacts

1 artifact

mnist_test.safetensors

safetensors · 20.6 KB · SHA-256 482cae8a1605…ed27 · Hugging Face

Download file

Source excerpts

2 excerpts
ReadmeAug 19huggingface.co/aplominski/mnist-4.5k

--- license: mit pipeline_tag: image-classification --- # Lightweight MNIST CNN (4.5K Parameters) This is an ultra-lightweight Convolutional Neural Network (CNN) with only 4.5K parameters, trained on the classic MNIST dataset for handwritten digit recognition. Despite its minimal size, the model achieves **94.48% accuracy** on the test split, making it highly efficient for edge devices or CPU-only environments. The full training workflow and source code can be found on [GitHub](https://github.com/aplominski/mnist-4.5k) and weights can be found on [Hugging Face](https://huggingface.co/aplominski/mnist-4.5k) ## Model Performance - **Task:** Image Classification (Handwritten Digits 0-9) - **Dataset:** MNIST - **Test Accuracy:** 94.48% - **Parameter Count:** ~4,500 ## Quick Start / Usage You can load and use this model directly using the code in github repository

NoteAug 19huggingface.co/aplominski/mnist-4.5k

Source context: 0 downloads · 0 likes · Pipeline image-classification · Repo aplominski/mnist-4.5k