Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
Network Architecture: - Nemotron 3 Nano LLM (30B A3B) — 31B-parameter Mamba2-Transformer hybrid MoE backbone with ~3B active parameters per token.
text + image → text + image · made by NVIDIA
Sold by
Nobody in the catalogue publishes a price for this yet.
About
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 — a text and images model from NVIDIA.
It takes text and images and returns text and images. It was published in April 2026. The catalogue files it under image and reasoning. Its weights are published under the other licence, which attaches conditions the plain open licences do not.
Every current figure
- Maker
- NVIDIA
- Register
- model
- Takes
- text + image
- Returns
- text + image
- Published
- April 2026
- Parameters
- 33 billion · read from its own weights
- Licence
- other
Known as 1 name
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16