Netron

Open-source neural network model viewer for macOS, Windows, Linux and browsers, with support for ONNX, PyTorch, TensorFlow Lite and Core ML.

Netron displays neural network and machine learning models as visual graphs. Developers and researchers can inspect a model's structure through desktop apps for macOS, Windows and Linux, or through the browser viewer at netron.app.

It reads ONNX, TensorFlow Lite, PyTorch, torch.export, ExecuTorch, TorchScript, TensorFlow, Core ML, OpenVINO and Keras models. Other supported formats include Caffe, Darknet, Safetensors and NumPy.

Support for MLIR, JAX, GGUF, RKNN, ncnn, MNN, PaddlePaddle and scikit-learn is experimental. Netron is a model viewer rather than an inference runtime. The JavaScript project is open source under the MIT license.

Model Inspection and Visualization macOS Windows Linux Web GGUF ONNX

Are you the owner or maker of Netron?

Claim this page with an email at netron.app. Netron gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.

Want more people to find Netron?Promote it

Something wrong or outdated on this page?

Similar to Netron

View all tools

gollama

An open-source Ollama model manager for macOS and Linux, with a terminal interface for model cleanup, inspection and memory estimates. MIT licensed.

1.8KUpdated 19 hours agoMIT

macOS · Linux#Ollama integration

gollama is a terminal app for people managing a local LLM collection in Ollama on macOS or Linux. It puts model details and management actions in one keyboard-driven view, useful when you need to compare downloaded models or clear out ones you no longer use. It's open source under the MIT license.

Model Hubs and DownloadersModel Inspection and Visualization

TensorBoard

An open-source ML visualization tool that runs locally or on your server, works offline, and compares TensorFlow training metrics and model graphs.

7.2KUpdated 1 month agoApache-2.0

macOS · Web#Works offline

TensorBoard is a browser-based toolkit for inspecting TensorFlow experiments on your own machine or server. It's for researchers and ML developers who need to understand training behavior, compare runs, and investigate model performance. It works entirely offline, including behind a corporate firewall or in a datacenter, so experiment data can stay within your own environment.

MediaPipe

An open-source toolkit for on-device AI across mobile, web and desktop. Apache 2.0 licensed; input stays local, while API metrics go to Google.

37.1KUpdated 19 hours agoApache-2.0

iOS · Android · Web

MediaPipe is an open-source toolkit for developers adding on-device AI to applications on Android, iOS, the web, desktop and edge devices. It pairs pretrained models with APIs for specific tasks, so developers can use existing solutions or customize them for their applications. The project uses the Apache 2.0 license.