Skip to content

Neural Amp Modeler Review

Neural Amp Modeler (NAM) is a free, open-source project that uses deep learning to capture guitar amps and pedals as model files, and a free plugin to play them in your DAW. For guitarists and gear builders.

Free · Web · API

Stork's verdict on Neural Amp Modeler

Neural Amp Modeler is a free, open-source way to capture and play real amps; ideal if you record on a computer and do not mind sourcing your own cab IRs.

Neural Amp Modeler reviewed by Stork AI · stork.ai/en/neural-amp-modeler

stork
I am a flat drawing.
One flat drawing and one typed sentence.
This drawing was never animated.
A photo, a cartoon, a painting or a 3D character. From 10 cents a minute. Free to try.
Make a photo talkDevelopers: there is an API

What Neural Amp Modeler does

Neural Amp Modeler (NAM) trains a neural network to imitate a specific guitar amplifier or pedal. You play a standard test signal (the reamp files NAM provides) through your gear, record the output, and NAM's trainer learns the difference and exports a .nam model file. Training runs in the browser through Google Colab with nothing installed, or locally with the Python trainer from PyPI (neural-amp-modeler, version 0.13.0, Python 3.10 or later), with step-by-step videos for Windows and Mac. Most players never train a model themselves: they download captures other people have made from TONE3000, a community library NAM points to.

To play models, NAM offers Gateway, a free VST3/AU plugin and standalone desktop app for Windows 10 or later and macOS 10.15 or later, plus ParametricOD, a concept plugin that models an overdrive across the full range of its knobs and switches. The code lives in three MIT-licensed repositories: the trainer, the core DSP library and the iPlug2-based plugin; a community LV2 build covers Linux. The project is maintained by Steven Atkinson, funded by donations through Ko-fi, and its core is used in commercial products: NAM's site lists builders including Darkglass, Two Notes, Hotone, Valeton and MOD Audio.

Neural Amp Modeler pricing

NAM has no paid plan. The trainer, the Gateway and ParametricOD plugins and the source code are free, and the project accepts voluntary donations.

PlanPriceIncluded
Neural Amp Modeler$0Gateway and ParametricOD plugins (VST3, AU, standalone), Colab and local trainers, MIT-licensed source code
Donation (optional)Any amountVoluntary support for the project via Ko-fi

Training in the browser uses Google Colab, which has its own free and paid tiers; local training runs on your own computer. Hardware units and third-party plugins that load NAM models are sold separately by their makers.

Prices checked on the vendor's pricing page on November 10, 2026 (NAM has no pricing page; the users, code and donate pages were checked). See NAM for users and Donate.

Key features

What the NAM project provides:

  • Deep-learning captures of amps and pedals saved as .nam model files
  • Browser-based training through Google Colab, no install needed
  • Local Python trainer on PyPI for Windows and Mac
  • Standardized reamp files so captures are made the same way
  • Gateway plugin (VST3, AU) and standalone app for Windows and macOS
  • ParametricOD concept plugin that models an overdrive across its knob range
  • Three MIT-licensed repositories for trainer, core DSP and plugin
  • Models shared through the community library TONE3000

Who Neural Amp Modeler is best for

NAM suits guitarists and bassists who record or practise through a computer and want accurate captures of real amps without paying for an amp sim, and players who own a favorite amp or pedal and want to capture it themselves. It also suits developers and hardware makers, since the MIT license lets them build NAM into products.

If you want a polished, all-in-one amp sim with cabinets, effects and preset management, Positive Grid BIAS FX is a commercial option. For capture-based tone in a dedicated pedal or plugin with vendor support, look at IK Multimedia TONEX or the Neural DSP Quad Cortex. Another free, open-source neural plugin is GuitarML Proteus.

What users say

In a 2023 review, ElectrikJam found the sound convincing, especially for high gain, and liked the community library, which includes rare amps other modelers skip. The same review lists limits: no cabinet impulse responses are included, community captures vary in quality, captures are snapshots of one knob setting, and training your own model works best with a dedicated GPU. Guitar.com reported in September 2026 that TONE3000 released a free plugin giving access to more than 700,000 NAM captures and impulse responses, with a newer NAM A2 engine developed together with NAM's creator.

Pros

  • Completely free, with MIT-licensed source code
  • Capture your own amps and pedals, in the browser or locally
  • Huge community library of shared captures on TONE3000
  • Plugin and standalone app for both Windows and macOS
  • Built into hardware and plugins from several commercial makers

Cons

  • Captures are snapshots of one setting, not full knob control
  • No cabinet impulse responses included by default, per reviewers
  • Quality of community captures varies
  • Local training is slow without a dedicated GPU, per reviewers

Frequently asked questions

Is Neural Amp Modeler free?

Yes. The trainer, the Gateway plugin and the source code are free and released under the MIT license. The project accepts optional donations via Ko-fi. Checked on November 10, 2026.

How do I make my own NAM capture?

Download NAM's standard reamp files, play them through your amp or pedal and record the output, then train a model in your browser with the Google Colab trainer or locally with the Python trainer from PyPI. The result is a .nam file you load in Gateway.

Where can I download NAM models?

NAM points users to TONE3000, a community-organized online library where people share their captures. You can also train captures of your own gear.

Which platforms does the NAM plugin support?

Gateway runs as a VST3 or Audio Unit plugin and as a standalone app on Windows 10 (64-bit) or later and macOS 10.15 or later. For Linux, the plugin repository points to a community LV2 build.

Does NAM include cabinet simulation?

Captures typically model an amp or pedal, and reviewers note NAM does not ship cabinet impulse responses by default, so you add your own IR loader and IRs for a full amp-and-cab sound.

Can I use NAM on stage?

Yes, through hardware from other companies. NAM's builders page lists makers such as Darkglass, Two Notes, Hotone and Valeton whose products use NAM technology.

Compare Alternatives

Neural Amp Modeler

Free · Web · API

From the Stork blog

Enjoying this? Get one like it in your inbox each morning.

one email a day · unsubscribe in two clicks · no third-party tracking