Expanded hardware support for imported models in OCI Generative AI

Services: Generative AI
Release Date: October 15, 2026

OCI Generative AI model import now supports more hardware options for the following models.

The following table lists the minimum dedicated AI cluster unit shape for each supported hardware family.


Model	Minimum Unit Shape by Hardware Family
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4	`H100_X8` `H200_X4` `B200_X2`
zai-org/GLM-5.3-Flash	`H100_X8` `H200_X4` `B200_X4`
Qwen/Qwen2.5-VL-3B-Instruct	`A100_40G_X1` `A100_80G_X1` `H100_X1` `H200_X1`
Qwen/Qwen2.5-VL-7B-Instruct	`A10_X4` `A100_40G_X2` `A100_80G_X1` `H100_X1` `H200_X1`
Qwen/Qwen2.5-VL-32B-Instruct	`A100_40G_X4` `A100_80G_X2` `H100_X2` `H200_X1`

For the complete list of models that you can import, see Models for Import. For hardware availability by region, see Hardware Unit Shapes by Region. For deployment steps, see Managing Imported Models.