Import NVIDIA Nemotron 3 Super and Ultra in US Government Cloud and US Defense Cloud
- Services: Generative AI, Oracle Cloud Infrastructure Government Cloud
- Release Date: October 26, 2026
You can now import the following NVIDIA Nemotron 3 models into OCI Generative AI in US Gov West (Phoenix) (OC2) and US DoD West (Phoenix) (OC3), host them on dedicated AI clusters, and create endpoints for inference:
Both models support the TEXT_TO_TEXT capability. The minimum dedicated AI cluster unit shape for each model in these two government regions is B300_X2. To use B300 units in a government region, request a service limit increase for dedicated-unit-b300-count.
For model details and minimum unit shapes across supported hardware families, see Compatible NVIDIA Nemotron Models. Hardware availability varies by region. For regional hardware availability and B300 service-limit instructions, see Hardware Unit Shapes by Region. For deployment steps, see Managing Imported Models.