# Nutanix @ GTC Berlin: From Open Models to Governed, Production-Ready AI

DevFeed: [Nutanix @ GTC Berlin: From Open Models to Governed, Production-Ready AI](<https://devfeed.tech/articles/nutanix-gtc-berlin-from-open-models-to-governed-production-ready-ai-93955.md>)

Original publisher: [Read original article](<https://www.nutanix.com/blog/nutanix-at-gtc-berlin>)

Author: Fahima Zahir

Published: 2026-10-21T04:30:00Z

Content type: news

Language: en

Sources: [Nutanix](<https://devfeed.tech/sources/nutanix.md>)

Topics: [nutanix](<https://devfeed.tech/topics/nutanix.md>), [Open Source Models & Datasets](<https://devfeed.tech/topics/open-source-models-datasets.md>), [KServe](<https://devfeed.tech/topics/kserve.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-runtimes](<https://devfeed.tech/tags/agent-runtimes.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-cloud](<https://devfeed.tech/tags/ai-cloud.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-ml](<https://devfeed.tech/tags/ai-ml.md>), [amd](<https://devfeed.tech/tags/amd.md>), [aos-storage](<https://devfeed.tech/tags/aos-storage.md>), [bare-metal](<https://devfeed.tech/tags/bare-metal.md>), [berlin](<https://devfeed.tech/tags/berlin.md>), [blog-category](<https://devfeed.tech/tags/blog-category.md>), [bof-consideration](<https://devfeed.tech/tags/bof-consideration.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [enterprise-ai](<https://devfeed.tech/tags/enterprise-ai.md>), [gtc](<https://devfeed.tech/tags/gtc.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [models](<https://devfeed.tech/tags/models.md>), [multicloud-kubernetes](<https://devfeed.tech/tags/multicloud-kubernetes.md>), [nutanix](<https://devfeed.tech/tags/nutanix.md>), [nutanix-cloud-platform-ncp](<https://devfeed.tech/tags/nutanix-cloud-platform-ncp.md>), [nutanix-data-services-for-kubernetes-ndk](<https://devfeed.tech/tags/nutanix-data-services-for-kubernetes-ndk.md>), [nutanix-enterprise-ai-nai](<https://devfeed.tech/tags/nutanix-enterprise-ai-nai.md>), [nutanix-kubernetes-platform-nkp](<https://devfeed.tech/tags/nutanix-kubernetes-platform-nkp.md>), [open](<https://devfeed.tech/tags/open.md>), [production](<https://devfeed.tech/tags/production.md>), [use-cases](<https://devfeed.tech/tags/use-cases.md>)

## AI overview

Nutanix describes an effort to connect open models and agent runtimes with governed AI infrastructure across on-premises, hybrid, and AI cloud environments. At GTC Berlin, it plans to show NVIDIA Vera-based agentic workloads, starting with Nutanix Kubernetes Platform (NKP) on bare metal and expanding to AHV as technical validation progresses. It is also working to make NVIDIA OpenShell, a sandboxed runtime with policy controls for agents, easier to deploy through the NKP catalog. Planned collaborations with Supermicro focus on private inference using Supermicro systems, NVIDIA GPUs and networking, and Nutanix Agentic AI software; work with Netris targets multitenant AI infrastructure with automated networking, tenant isolation, and self-service across bare-metal and virtualized environments. Nutanix also cites support for open models and contributions to KServe, Agent Router, MLCommons, and the Open Secure AI Alliance. The text presents these as ongoing or planned work, not completed deployments.

## Source excerpt

Tips from experts, thoughts from leaders, news from the front line. Join the conversation beyond hyperconverged infrastructure to the enterprise cloud.