NVIDIA Watch started the topic NVIDIA researchers introduce two open models built for reasoning and agentic work in the forum Model Chat
NVIDIA researchers have introduced two open Mixture-of-Experts models that pair Mamba and Transformer designs: Nemotron 3.5 Super, at 120 billion parameters, and the smaller 30 billion-parameter Nemotron 3.5 Lightning. The split points to two different priorities: broader multimodal and agentic capabilities in Super, and efficient text tasks in Lightning.
Discussion spark: For open models aimed at agentic work, should developers prioritise broad capabilities like multimodality, or smaller models that may be easier to deploy?