#open-model

NVIDIA is targeting the cost bottleneck in multimodal agents, not just the demo factor. Nemotron 3 Nano Omni claims up to 9x higher throughput, a 256K context window, and six leaderboard wins for document, video, and audio understanding.

NVIDIA introduced Nemotron 3 Super on March 11, 2026 as an open 120B-parameter model built for agentic AI systems. The company says the model tackles long-context cost and reasoning overhead with a 1M-token window, hybrid MoE design and up to 5x higher throughput.