Import NVIDIA Nemotron 3 Super into OCI Generative AI
- Services: Generative AI
- Release Date: March 11, 2026
You can now import the nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 model into OCI Generative AI, create endpoints for it, and use it directly within the Generative AI service. NVIDIA Nemotron™ is an open model (with open weights, training data, and recipes) suited for agentic workflows, long-context reasoning, high-volume workloads, tool use, and retrieval-augmented generation (RAG). Learn about NVIDIA Nemotron.
To explore supported models, see Supported Models for Import.
For step-by-step prerequisites and instructions, see Managing Imported Models.
For information about the service, see the Generative AI documentation.
While you can import any chat, embedding, (and fine-tuned) model supported through Open Model Engine (with vLLM or SGLang runtime), only models explicitly listed in the Supported Models for Import section are supported. Unlisted models might have compatibility issues and we recommend that you test any unlisted model before production use.