ModelNemotronH-Omni
NemotronH Omni
A multimodal joint reasoning model introduced by NVIDIA that integrates a Mamba-Transformer hybrid language model, a RADIO vision encoder, and a Parakeet audio encoder. It supports unified autoregressive inference over text, images, video, and audio.
Timeline (last 90 days)
Oct 4
NemotronH Omni is a multimodal reasoning model from NVIDIA that combines NemotronH's Mamba-Transformer hybrid language model with the RADIO visual encoder and an optional Parakeet audio encoder, enabling joint autoregressive reasoning over text, images, video, and audio.
Unverified50%