- Home
- Guitar Amp Software
- Neural Amp Modeler
Neural Amp Modeler
What it is
Neural Amp Modeler (NAM) uses deep learning to create models of guitar amplifiers and pedals. The project is free and open source, with three code repositories under permissive licenses that welcome contributions. Users can train models online in Google Colab or install the Python-based trainer locally from PyPI. The Gateway plugin loads and plays snapshot models of gear, while ParametricOD demonstrates modeling across an overdrive’s knobs and switches. The plugin repository produces VST3 and AU plugins as well as a standalone desktop application. Models can be shared through TONE3000, a community-organized online library. NAM supports Windows, macOS, Linux, Raspberry Pi, embedded systems, and websites. Existing A1 models remain supported in NeuralAmpModelerCore and NeuralAmpModelerPlugin. Builders can incorporate NAM’s open-source modeling technology into their own products. Its training code depends on PyTorch Lightning; version 0.12.3 excludes compromised Lightning versions 2.6.2 and 2.6.3. The listed plan is free.
For and against
For
- Train models in Google Colab or locally from PyPI.
- Plugin repository produces VST3 and AU plugins.
- Models can be shared through TONE3000.
- Existing A1 models remain supported.
Against
- Training code depends on PyTorch Lightning.
- The security notice names compromised Lightning versions 2.6.2 and 2.6.3.
The verdict
NAM offers tools to train, play, and share amplifier and pedal models, with plugin and standalone options. The training code’s PyTorch Lightning dependency is a relevant consideration for users managing that setup.
Who it suits
NAM suits guitarists interested in modeling amplifier or pedal sounds, as well as people who want to train and share models. Its open-source modeling technology is also intended for builders incorporating it into their own products.
Plans and prices
Neural Amp Modeler
open-source project · continuous development
Read 1 Oct 2026 · neuralampmodeler.com
On the record
- A2 compatibility
- Existing A1 models remain supported in NeuralAmpModelerCore and NeuralAmpModelerPlugin.neuralampmodeler.com · read 1 Oct 2026
- Builder integration
- Builders can use NAM's open-source modeling technology in their own products.neuralampmodeler.com · read 1 Oct 2026
- Gateway plugin
- Gateway loads and plays snapshot models of users' favorite gear.neuralampmodeler.com · read 1 Oct 2026
- Model sharing
- Users can share models through TONE3000, a community-organized online library.neuralampmodeler.com · read 1 Oct 2026
- Model trainer
- Users can train models online in Google Colab or install the Python-based trainer locally from PyPI.neuralampmodeler.com · read 1 Oct 2026
- Open source
- NAM has three code repositories available under permissive open-source licenses and open to contributions.neuralampmodeler.com · read 1 Oct 2026
- Parametric modeling
- ParametricOD demonstrates NAM parametric modeling across the full range of an overdrive's knobs and switches.neuralampmodeler.com · read 1 Oct 2026
- Plugin formats
- The plugin repository creates VST3 and AU plugins plus a standalone desktop application.neuralampmodeler.com · read 1 Oct 2026
- Security notice
- NAM's training code depends on PyTorch Lightning, and version 0.12.3 excludes compromised Lightning versions 2.6.2 and 2.6.3.neuralampmodeler.com · read 1 Oct 2026
- Support
- Builders seeking help can contact [email protected].neuralampmodeler.com · read 1 Oct 2026
- Supported systems
- NAM runs on Windows, macOS, Linux, Raspberry Pi, embedded systems, and websites.neuralampmodeler.com · read 1 Oct 2026
- What it does
- Neural Amp Modeler uses deep learning to create models of guitar amplifiers and pedals with state-of-the-art accuracy.neuralampmodeler.com · read 1 Oct 2026
