Skip to main content

Ollama Workload

Ollama Workload is a robust deployment solution available on Microsoft Azure, designed for high scalability, enhanced security, and optimal performance. This solution streamlines your machine learning model deployments while ensuring seamless integration with Azure's trusted infrastructure.

info

GCP support is pending due to the absence of Confidential Computing support.

Model Configuration

Specify your model using the format: modelname:version

Examples:

llama3.3:70b-instruct-fp16

Available Models

A full list of supported models, including names and versions, can be found on the Ollama Model Hub.