ai

Deploying OpenAI’s GPT-OSS model on Kubernetes with Ollama

A step-by-step guide to self-hosting LLMs in a homelab

Madhan published on August 10, 2025

4 min, 695 words

Tags: nvidia homelab ollama gpu proxmox k8s openai ai

Adding Nvidia GPU boost to Proxmox k8s using Pulumi and Kubespray

A step-by-step guide to leveraging Nvidia GPUs in Kubernetes

Madhan published on July 17, 2025

5 min, 970 words

Tags: nvidia homelab proxmox gpu proxmox pulumi kubespray k8s ai

Making my homelab server AI ready with Nvidia GPU — Part II

A End-to-End guide on GPU Passthrough

Madhan published on July 06, 2025

3 min, 518 words

Tags: gpu homelab proxmox ai nvidia pulumi

Making my homelab server AI ready with Nvidia GPU — Part I

A step-by-step upgrade from server to AI workstation

Madhan published on June 25, 2025

3 min, 579 words

Tags: gpu homelab ai nvidia egpu

Simplifying Bank statement analysis using Marker and Ollama

A guide to using Streamlit, Marker, Ollama and the Phi-4 model for seamless data extraction

Madhan published on January 26, 2025

4 min, 651 words

Tags: python phi4 devcontainer docker streamlit ollama ai