Cite
Notes
Only stored in your browser.
Attribution
Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
arXiv 2025
Pretraining Large Language Models with NVFP4
from 2 papers
Aaron Blakeman
Aditya Vavre
Alex Kondratenko
Ben Lanir
Bita Darvish Rouhani
Bryan Catanzaro
researcher
Carlo del Mundo
Darko Stosic
Deepak Narayanan
Dong Ahn