#1313th of 168 in ML frameworks and libraries
netron
Viewer for neural network and machine learning model graphs
Live demo ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 33.7k
- License
- MIT
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- JavaScript
32,581 on 20 Apr 202633,677 on 9 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Netron opens model files and renders their layer graphs, with node attributes and tensor details. It reads ONNX, TensorFlow Lite, PyTorch, TorchScript, TensorFlow, Core ML, OpenVINO, Keras, Caffe, Darknet, Safetensors and NumPy, with experimental support for GGUF, MLIR, JAX and others. It runs in the browser, as a desktop app on macOS, Linux and Windows, or as a Python package.
Who it is for: ML engineers inspecting model architectures across formats
Strengths
- Covers many formats: ONNX, TFLite, PyTorch, Core ML, OpenVINO, Keras, Safetensors and more
- Hosted browser version at netron.app can open a model from a URL
- Also ships as macOS, Linux and Windows installers and a pip package
- MIT license
Weaknesses
- GGUF, MLIR, JAX, ncnn, MNN, PaddlePaddle and scikit-learn support is experimental
- Viewer only: does not edit, convert or run models
- No Docker image or compose file provided
What it needs
- no GPU
- Models: ONNX, TensorFlow Lite, PyTorch, torch.export, ExecuTorch
Quick answers
Is netron open source?
Yes. Its code is on GitHub under the MIT license.
Does netron need a GPU?
No, it runs without one.
Also in ML frameworks and libraries
See all 168| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd | 93 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and training scripts | 93 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 92 out of 100 |