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)→
More from Models
- Is DeepSeek's rumored K3 a scaled-down model, or something bigger? X users debate — teortaxesTex · 2026-09-11
- DeepSeek update keeps cache hits mid-conversation, cuts costs 36.6% — teortaxesTex · 2026-09-11
- AI Sextet offers 6 models free and unlimited for 14 days, including DeepSeek and Qwen — airesearch12 · 2026-09-11
- BullshitBench update: GPT-6-Astra beats all prior OpenAI models but still trails Anthropic — scaling01 · 2026-09-11
- Astra Scores 83% on GauntletBench, First Computer-Use Agent to Beat Human Baseline — ducha_aiki · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11