Netron

Netron is a desktop application for viewing neural network, deep learning and machine learning models as interactive graphs.

  • Development
Netron is a desktop application for viewing neural network, deep learning and machine learning models as interactive graphs. It opens model files in formats such as ONNX, TensorFlow, TensorFlow Lite, PyTorch, Core ML, OpenVINO and Keras, showing layers, parameters and subgraphs as a navigable diagram. Machine-learning developers and hobbyists use it to quickly verify, debug or understand models they have built, trained or downloaded, on macOS, Windows, Linux or in the browser.

Platform availability

Available on 4 of 10 platforms

  • Unraid (not listed)
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac
  • Windows
  • Linux
  • Any server

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

86/100 Excellent

Maintained
100last commit 2 days ago
Popular
9133,709 GitHub stars
Easy to install
554 install platforms, install notes
Light to run
No data
Security check
82no serious findings, 3 minor, CI, tests

Based on 4 of 5 factors.

Availability: platform listings confirmed today

GitHub stars
33,709
Open issues
19
Last commit
2026-11-19
Latest release
v9.3.6
License
MIT
Activity
steady

Checked 3 days ago - source: GitHub (lutzroeder/netron)

Resources & Compatibility

Requirements not published yet.

Checked 3 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Install A browser version is available without installing. Desktop installation: on macOS download the .dmg file or run 'brew install --cask netron'; on Linux install the .deb or .rpm package; on Windows use the .exe installer or run 'winget install -s winget netron'. A Python package is also available ('pip install netron', then run 'netron [FILE]'). source
  • Desktop install options Netron also runs directly in a browser via the website link. For desktop: on macOS download the .dmg from the releases page or run 'brew install --cask netron'; on Linux install the .deb or .rpm package; on Windows run the .exe installer or install via Winget. source

Fetched 3 days ago - each note links to its source

Alternatives (7)

  • Deep playground - Deep playground is an interactive visualization of neural networks, written in typescript using d3.js and TensorFlow.
  • NEST Desktop - NEST Desktop is a web-based application which provides a graphical user interface for NEST Simulator.
  • Neuronify - An educational neural network app.
  • PyTorch - PyTorch enables fast, flexible experimentation and efficient production through a hybrid front-end, distributed training, and ecosystem of…
  • llama.cpp - Llama.cpp is a pure C/C++ inference engine for large language models, including Meta's LLaMA.
  • model-explorer
  • tensorflow - TensorFlow is an open source software library for machine learning in various kinds of perceptual and language understanding tasks.

Checked 3 days ago - source: AlternativeTo

Common questions

Can I view Netron model files without installing a desktop app?

Yes, a browser version is available without installation. You can also install desktop packages or the Python package for local use.

Which model formats are only experimentally supported by Netron?

Netron has experimental support for MLIR, JAX, GGUF, RKNN, ncnn, MNN, PaddlePaddle, and scikit-learn. These are separate from its core listed formats.

Why would I choose to run Netron locally instead of using the public web viewer?

Model files can be intellectual property, and uploading a sensitive model to a public browser tab may violate policy. Running Netron on your own machine or an internal server keeps the weights on infrastructure you control.

Is the Python package likely to need extra care on older Python versions?

Old environments such as Python 2.7 may have compatibility issues, and a guide provides avoidance advice. The issue is covered as part of a broader installation and usage guide.

Answers sourced from blog.csdn.net, github.com, swifthost.ca

Community

Collected 3 days ago - public community threads