← Back to AI News

NVIDIA releases Nemotron 3 Nano Omni — open omni-modal model at 30B parameters
Chris Harper
1 min read
May 28, 2026
AI
AI News
LLM
NVIDIA's new model unifies vision, audio, and language in a single 30B-parameter mixture-of-experts architecture. Open weights and omni-modal capability in a relatively compact model could be significant for edge and on-device use cases.
Source: LLM Stats