NVIDIA Nemotron 3.5 Lightning Goes Live on Crusoe for High-Volume Agent Inference

Scobleizer · x · 2026-08-11

Crusoe announced that NVIDIA Nemotron 3.5 Lightning is now available on its managed inference platform. The model is a 30B parameter MoE with 3B active parameters, designed for high-volume, specialized tasks in agent workflows.

Crusoe offers flexible deployment options including Serverless and Self-Serve, utilizing MemoryAlloy technology to optimize cluster memory routing and reduce prefill computation.

Original post →

More from Infra

Infra channel →