Model Availability by Platform
Where to Find AI21’s Jamba Models
AI21’s Jamba models are available across multiple leading cloud platforms and model hubs. Choose the platform that best fits your infrastructure and deployment needs.
Quick Platform Overview
| Platform | Managed | Self-Deploy | Latest Version |
|---|---|---|---|
| AWS Bedrock | ✅ | - | 1.5 |
| AWS SageMaker | - | ✅ | 1.5 |
| GCP Vertex AI | ✅ | - | 1.5 |
| GCP Model Garden | - | ✅ | 1.6 |
| Microsoft Azure | ✅ | - | 1.5 |
| HuggingFace | - | ✅ | 1.6 |
Amazon Web Services (AWS)
Managed Services
Jamba Large 1.5
Platform: AWS Bedrock (Managed)
Best for: Enterprise AWS users, serverless applications, pay-per-use pricing
Jamba Mini 1.5
Platform: AWS Bedrock (Managed)
Best for: Enterprise AWS users, serverless applications, pay-per-use pricing
Self-Deployment
Jamba Large 1.5
Platform: AWS SageMaker
Best for: ML Engineers, Custom infrastructure, on-premises deployment
Jamba Mini 1.5
Platform: AWS SageMaker
Best for: ML Engineers, Custom infrastructure, on-premises deployment
Coming Soon
Jamba Large 1.6
Platform: AWS Bedrock
Status: Coming Soon 🔄
Jamba Mini 1.6
Platform: AWS Bedrock
Status: Coming Soon 🔄
Google Cloud Platform (GCP)
Managed Services
Jamba Large 1.5
Platform: GCP Model Garden (Serverless)
Best for: Google Cloud users, Vertex AI
Jamba Mini 1.5
Platform: GCP Model Garden (Serverless)
Best for: Google Cloud users, Vertex AI
Self-Deployment
Coming Soon
Jamba Mini 1.6
Platform: GCP Model Garden (Self-Deploy)
Status: Coming Soon 🔄
Microsoft Azure
Managed Services
Jamba Large 1.5
Platform: Microsoft Azure
Best for: Azure users, serverless applications
Jamba Mini 1.5
Platform: Microsoft Azure Best for: Azure users, serverless applications
HuggingFace
Jamba Large 1.6
Platform: HuggingFace
Best for: Research, open-source projects, local development, fine-tuning
Jamba Mini 1.6
Platform: HuggingFace
Best for: Research, open-source projects, local development, fine-tuning
Interested in Self-Deploy?
For self-deployment on your own infrastructure, check out our vLLM deployment guide for step-by-step instructions and examples.