NVIDIA Open-Sources Nemotron 3.5 Lightning for High-Volume Agentic Execution

NVIDIAAI · x · 2026-08-11

NVIDIA has fully open-sourced the Nemotron 3.5 Lightning model, built specifically for the high-volume execution tasks of long-running agents. The model is now available on Hugging Face.

The release includes not just the model weights, but also the data and training recipes. Featuring a 30B MoE architecture (with 3B active parameters) and a 1M token context length, it aims to deliver efficient agentic execution at a lower cost.

Related event: NVIDIA Open-Sources Nemotron Model and Agent Router(37 posts)→

Original post →

More from Models

Models channel →