# Dedicated Inference

Deploy and run AI models on dedicated GPUs.

[Read more](https://www.exoscale.com/ai-cloud-infrastructure/dedicated-inference/)

{{< cards cols="2" >}}

  {{< card
  link="ai-model/"
  icon="exo-ai-prod"
  title="AI Model"
  subtitle="Lifecycle of AI Models." >}}

  {{< card
  link="deployment/"
  icon="exo-gpu"
  title="Deployment"
  subtitle="Deployments are loaded model instances ready for inference." >}}

{{< /cards >}}