Compatible Mistral 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.
These models have a high-performance, decoder-only Transformer architecture featuring Sliding Window Attention (SWA) for efficient long-context handling and optional Grouped Query Attention (GQA) for improved scalability. For more details, see Mistral in the Hugging Face documentation.
Mistral
| Hugging Face Model ID | Model Capability | Recommended Dedicated AI Cluster Unit Shapes |
|---|---|---|
| mistralai/Mistral-Medium-3.5-128B | TEXT_TO_TEXT |
|
| mistralai/Devstral-2-123B-Instruct-2512 | TEXT_TO_TEXT |
|
| mistralai/Mixtral-8x7B-Instruct-v0.1 | TEXT_TO_TEXT | A100_80G_X2 |
| mistralai/Mistral-Nemo-Instruct-2407 | TEXT_TO_TEXT | A100_80G_X1 |
| mistralai/Mistral-7B-Instruct-v0.3 | TEXT_TO_TEXT | A100_80G_X1 |
| mistralai/Mistral-7B-Instruct-v0.2 | TEXT_TO_TEXT | A100_80G_X1 |
| mistralai/Mistral-7B-Instruct-v0.1 | TEXT_TO_TEXT | A100_80G_X1 |
| intfloat/e5-mistral-7b-instruct | EMBEDDING | A10_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.