Compatible NVIDIA Nemotron Model
You can import large language models from Hugging Face and OCI Object Storage buckets into OCI Generative AI, create endpoints for those models, and use them in the Generative AI service.
NVIDIA Nemotron™ is a family of open models with open weights, training data, and recipes, suited for agentic workflows, long-context reasoning, high-volume workloads (for example, IT ticket automation), tool use, and RAG. For the compatible models on Hugging Face, see the links in the following table. Learn about NVIDIA Nemotron.
NVIDIA Nemotron
| Hugging Face Model ID | Model Capability | Recommended Dedicated AI Cluster Unit Shape |
|---|---|---|
| nvidia/Llama-3.1-Nemotron-Nano-8B-v1 | TEXT_TO_TEXT | A100_80G_X1 |
| nvidia/Llama-3.1-Nemotron-70B-Instruct-HF | TEXT_TO_TEXT | A100_80G_X4 |
| nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 | TEXT_TO_TEXT | B200_X4 |
| nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 | TEXT_TO_TEXT | H100_X8 |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 | TEXT_TO_TEXT | H100_X4 |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | TEXT_TO_TEXT | A100_80G_X1 |
Important
- For imported models, you can use the native context length specified by the model provider. However, the effective maximum context length is limited by the underlying hardware setup that you select for the hosting dedicated AI clusters in OCI Generative AI. To take full advantage of a model's native context length, you might need to provision more hardware resources.
- Use the fine-tuned models only if they match the compatible base model's transformer version and have a parameter count within ±10% of the original.
- For available hardware and steps on how to deploy the imported models, see Managing Imported Models.