NVIDIA Releases Audex-30B-A3B Audio Language Model

nvidia · hf · 2026-07-07

NVIDIA has released Nemotron-Labs-Audex-30B-A3B, a new model utilizing a MoE architecture (30B total parameters, 3B active). It focuses on audio-understanding and audio language modeling capabilities, supporting inference, SFT, and RL training. Positioned as a general-purpose reasoning model, it is open-sourced in transformers and safetensors formats.

Related event: NVIDIA Releases Open-Source Audio-Text LLM Audex-30B(9 posts)→

Original post →

More from Models

Models channel →