Introducing Neural Amp Modeler (NAM) Architecture 2 (A2)ToneHunt is now TONE3000Read blog

Browse TonesGet StartedNeural Amp Modeler (NAM)NAM A2 GuideImpulse Responses (IR's)Capture Your GearCapture InstructionsCategoriesGuidesBlogAboutUpload Models & IR'sTop CreatorsAPI DocsView More

Today we're launching Architecture 2 (A2), the next generation of Neural Amp Modeler (NAM) built by TONE3000, in partnership with NAM creator Steve Atkinson.<br>A2 lets anyone create hyper-accurate neural captures of analog gear, including amps, guitar and bass pedals, outboard gear, and full signal chains.<br>It sounds better than any modeler that has come before it, runs on hardware as small as a $3 chip, and is fully open source.<br>A2 marks a turning point for the industry in three ways:<br>Incredibly accurate sound. A2 beats Neural DSP V2, IK Multimedia ToneX V2, and Line 6 Proxy by a wide margin in both quantitative and blind listening tests (shown below).<br>Works anywhere. A2 runs in DAWs and even budget multi-fx pedals, with sound quality better than Quad Cortex at 50% CPU on a $3 ARM Cortex-M7 600MHz chip.<br>Fully open source. Any hardware or software maker can support A2 in their product with code that's freely available online.<br>A2 makes TONE3000 and Neural Amp Modeler possible on mass-market hardware.<br>Blackstar, Lava Music, Darkglass , HeadRush, Chaos Audio and Dimehead are all supporting A2, with dozens of major companies announcing support later this year.

"We’re excited to partner with Tone3000 and Steve Atkinson to bring native NAM support to the HeadRush platform. This Summer, Prime, Core, and Flex Prime users will be able to load NAM captures directly to their rigs, with no lossy conversion. Our touchscreen and integrated Wi-Fi will also provide onboard access to TONE3000’s growing library, making it easy to discover, download, and start playing with NAM captures directly on your HeadRush pedal.”<br>– Walter Skorupski, Senior Product Manager, HeadRush

This blog post is a high-level announcement. For a comprehensive breakdown of A2 visit NAM A2: The Complete Guide

How do I play through A2 models?<br>Browse and download A2 tones via TONE3000: tone3000.com/search<br>Download the latest NAM plugin "Gateway": neuralampmodeler.com/users<br>Choose Select model directory... in the plugin and select your downloaded A2 tones<br>The story behind A2<br>NAM launched as an open-source project in 2019 and quickly became the most accurate amp modeling technology available. The first iteration, Architecture 1 (A1), was designed by Steve Atkinson to run inside DAWs on computers, not embedded devices like multi-fx pedals.<br>A2 was developed by TONE3000 in partnership with Steve. Together, we rebuilt the architecture from the ground up to deliver better sound quality while using far fewer computational resources, opening the door for affordable multi-fx pedals and amps to run NAM natively on device.

A2 is the most accurate amp modeler ever<br>A2 captures sound virtually indistinguishable from the analog original. The bloom of a tube amp pushed into breakup, the sag of a fuzz pedal under a heavy chord, the snap of a transient through an analog compressor: A2 captures it all.<br>A2 represents dynamics, gain structure, frequency behavior, and transient handling more faithfully than any modeler that has come before it.<br>We verified this in two ways: head-to-head quantitative testing and large-scale blind listening tests.<br>Quantitative tests<br>We compared recordings of real gear against neural models from Neural Amp Modeler A2 and A1, Neural DSP Neural Capture V2, IK Multimedia's ToneX and Line6's Proxy. Each model was scored on how closely its output matched the original recording using four metrics: ESR, MAE, LOG_MEL and MRSTFT. Those scores were used to create head-to-head comparisons between models, using a single Bayesian Elo rating.<br>The Bayesian Elo score worked like a win/loss rating, where higher scores meant the model more consistently matched the real recording. The evaluation dataset spanned 39 tones, covering guitar and bass amps, amp and cab rigs, pedals, pedal and amp chains, outboard gear, and more. We modeled everything from sparkling Fender cleans to a vintage Neve 1073 to a dimed Mesa Boogie Dual Rectifier.<br>Amp Modeler Accuracy Test<br>Each model's output was compared against recordings of real gear using several error metrics (ESR, MAE, LOG_MEL, and MRSTFT). This chart shows Bayesian Elo ratings derived from ESR, where higher scores indicate lower measured error relative to the original amp, pedal, or signal chain.

Share<br>Bayesian Elo Comparison (ESR)<br>Mean ± 1 std across 39 tones, higher is better

IncludeNAM A1-Nano

Tone3000 - NAM Captures and IRs

Blind listening tests<br>We also ran a large-scale blind listening test using the MUSHRA methodology, the audio industry's gold standard for evaluating perceived sound quality, often used by organizations like the BBC and EBU.<br>Over 1,000 participants submitted more than 100,000 ratings, which might be the largest...