Kubernetes

Introduction This is part 2 in an ongoing series about building an open-source agentic coding platform. In part one I covered deploying Nutanix Enterprise AI 2.6 on bare-metal NKP with Pure FlashArray storage via Portworx CSI. In this post I’ll review model selection, deployment, tuning and integration with Opencode. Future posts will cover more on the agentic coding setup. This one is denser than part 1 but by the end you’ll have three production-tuned models, an Opencode integration, and a small arsenal of kubectl patch tricks to streamline endpoint management. ...

I’ve worked with Nutanix Enterprise AI (NAI) a lot over the last few months. I’ve deployed it across several Nutanix Kubernetes Platform (NKP) architectures: VMs on Nutanix HCI, VMs on Nutanix Cloud Platform with External Storage and bare-metal Ubuntu backed by Everpure. This post is about the last, the most unusual of the three and the platform for my broadest set of experiments. This will be the first in a series of posts about my work with this cluster. In this post I will focus on the architecture and initial set-up. Later I will cover post-deployment activities including break/fix troubleshooting, model deployment, tuning and other tips and trick. In the final post I will cover building up an open-source gstack-style agentic coding setup driven by OpenCode and leveraging Qwen3.6-27B-FP8, gemma-4-31B-it and gpt-oss-120b running on NAI. ...