Oracle Cloud Infrastructure Documentation

Compatible Google Models

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.

For models details, see the following links:

MedGemma

Google MedGemma 27B Text IT is a 27-billion-parameter language model based on the Gemma 3 architecture. Trained on medical literature and clinical records, the model is instruction-tuned (IT), enabling it to better follow user requests and help perform healthcare-focused tasks such as medical question answering, clinical support, and summarizing.

Compatible MedGemma Model
Hugging Face Model ID Model Capability Recommended Dedicated AI Cluster Unit Shape
google/medgemma-27b-text-it TEXT_TO_TEXT
  • A100_80GB_X2
  • H100_X2
  • H200_X1
  • B200_X1

Gemma

Compatible Gemma Models
Hugging Face Model ID Model Capability Recommended Dedicated AI Cluster Unit Shape
google/gemma-4-31B-it IMAGE_TEXT_TO_TEXT
  • A100_40GB_X2
  • A100_80GB_X2
  • H100_X2
  • H200_X1
  • B200_X1
google/gemma-3-4b-it IMAGE_TEXT_TO_TEXT A100_80G_X1
google/gemma-3-270m-it TEXT_TO_TEXT A100_80G_X1
google/gemma-3-27b-it IMAGE_TEXT_TO_TEXT A100_80G_X2
google/gemma-3-12b-it IMAGE_TEXT_TO_TEXT A100_80G_X1
google/gemma-3-1b-it TEXT_TO_TEXT A100_80G_X1
google/gemma-2-9b-it TEXT_TO_TEXT A100_80G_X1
google/gemma-2-27b-it TEXT_TO_TEXT A100_80G_X2
google/gemma-2-2b-it TEXT_TO_TEXT A100_80G_X1