NVIDIA Launches Nemotron 3.5 Lightning: 30B MoE with 4x Higher Throughput

willccbb · x · 2026-08-12

NVIDIA has released the Nemotron 3.5 Lightning model. Built on a 30B MoE architecture with 3B active parameters, it is designed for always-on agents to handle high-volume, specialized tasks.

It delivers up to 4x the output speed and 30% faster task completion compared to similar-sized models. Prime Intellect has announced Day-0 support, allowing developers to post-train the model for specific domains using prime-rl and Prime Lab.

Related event: NVIDIA Launches Nemotron 3.5 Lightning Model and NeMo Switchyard Router(45 posts)→

Original post →

More from coding & agent

coding & agent channel →