NVIDIA releases Nemotron 3.5 Lightning, an open 30B mixture-of-experts model for agents

NVIDIA's Hugging Face model card gives August 11, 2026 as the release date of NVIDIA-Nemotron-3.5-Lightning-30B-A3B, a model with 30B total and 3B active parameters built on a hybrid of Mamba-2, mixture-of-experts and attention layers, with reasoning that can be switched on or off through the chat template. The card lists the OpenMDW License Agreement, version 1.1, and points to a separate NVFP4 checkpoint for optimized inference. NVIDIA's developer blog says the model is designed for the high-volume execution work of long-running agents, ships with DFlash and DSpark draft models for speculative decoding, and is released with an open reinforcement learning dataset, Nemotron-RL Agentic Terminal Pivot. USASI has not tested the model.12

USASI. (2026, October 13). NVIDIA releases Nemotron 3.5 Lightning, an open 30B mixture-of-experts model for agents. United States of America Superintelligence. https://unitedstatesofamericasuperintelligence.com/news/nvidia-releases-nemotron-3-5-lightning/

@misc{usasi_news_nvidia_releases_nemotron_3_5_lightning,
  author = {{USASI}},
  title = {NVIDIA releases Nemotron 3.5 Lightning, an open 30B mixture-of-experts model for agents},
  year = {2026},
  month = oct,
  howpublished = {\url{https://unitedstatesofamericasuperintelligence.com/news/nvidia-releases-nemotron-3-5-lightning/}},
  note = {United States of America Superintelligence. Last updated 2026-10-13}
}