TM autoscale on-prem

Author: charlotte-hoblik

deploy-manage/autoscaling/trained-model-autoscaling.md

@@ -22,6 +22,8 @@ To fully leverage model autoscaling in {{ech}}, {{ece}}, and {{eck}}, it is high
 
 Trained model autoscaling is available for both {{serverless-short}} and Cloud deployments. In serverless deployments, processing power is managed differently across Search, Observability, and Security projects, which impacts their costs and resource limits.
 
+Trained model autoscaling is unavailable for on-premises. The used resources for trained model deployment are static, your available resources are segmented (low, medium, high) based on your settings.
+
 Security and Observability projects are only charged for data ingestion and retention. They are not charged for processing power (VCU usage), which is used for more complex operations, like running advanced search models. For example, in Search projects, models such as ELSER require significant processing power to provide more accurate search results.
 
 ## Enabling autoscaling through APIs - adaptive allocations [enabling-autoscaling-through-apis-adaptive-allocations]