Import Qwen 3 Embedding models into OCI Generative AI
- Services: Generative AI
- Release Date: March 11, 2026
You can now import the Qwen 3 Embedding models into OCI Generative AI, create endpoints for them, and use them directly within the Generative AI service. The Qwen 3 Embedding model series is designed for text embedding and reranking use cases and is available in several sizes. These models support multilingual and long-text scenarios and can be used for tasks such as text retrieval, code retrieval, text classification, text clustering, and bitext mining.
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.