Not established from the available sources.
NVIDIA · MODEL RELEASE TRACKER
Nemotron 3 Nano Omni
Nemotron 3 Nano Omni is presented in a Hugging Face / NVIDIA blog post as the Nemotron 'Seeing' component used in an interactive Halloween project; the post describes it as able to describe costumes (a vision-capable, multimodal model).CURRENT SNAPSHOT1/5 DIMENSIONS WITH DATA
The dimensions that change the decision.
Not established from the available sources.
ModalitiesDescribed in the article as a vision-capable (image) model used alongside text—i.e., a multimodal model (Seeing component).
Not established from the available sources.
Not established from the available sources.
VERIFIABLE FACTS
Every value stays attached to a source and date.
MODALITIES · ModalitiesDEVELOPER CLAIM
Described in the article as a vision-capable (image) model used alongside text—i.e., a multimodal model (Seeing component).
CAPABILITIES · Image-description capabilityDEVELOPER CLAIM
The article states Nemotron 3 Nano Omni 'describes costumes' (used to describe visitors' costumes in the MonsterHouse installation).
WHAT CHANGED