JCJim Chundevalelinaccidentalcomplexity.hashnode.dev·6d ago · 26 min readPart 4: An Edge AI Circus - Running Gemma 4 on a Pi 5 with OllamaIntroduction This is my build log. The goal was simple: run Google's Gemma 4 models locally on a 16 GB Raspberry Pi 5 with Ollama. No cloud. No GPU. Just a small board on a desk doing real inference f00
JCJim Chundevalelinaccidentalcomplexity.hashnode.dev·Jun 7 · 17 min readPart 3: The Brain, Hermes Agent, WhatsApp, and the Tiny Model Reality Check Introduction Parts 1 and 2 built the infrastructure: two HAT Pis running hailo-ollama on Hailo-10H silicon, Open WebUI sitting in front of them behind a clean API, SearXNG handling private web search,00
JCJim Chundevalelinaccidentalcomplexity.hashnode.dev·Jun 6 · 10 min readPart 2: Building the hailo-bridge and Solving the Streaming ProblemIntroduction In Part 1, we built the inference foundation and briefly enjoyed the dangerous illusion that everything was under control. Two HAT Pis were running hailo-ollama, Open WebUI was sitting in00
JCJim Chundevalelinaccidentalcomplexity.hashnode.dev·Jun 1 · 18 min readPart 1: Building a Self-Hosted AI Agent Cluster with Raspberry Pi 5 and Hailo AI HAT+ 2Introduction So there I was, staring at four Raspberry Pi 5s, two Hailo AI HAT+ accelerators, a growing pile of cables, and the uncomfortable realization that I had built a tiny data center to avoid s00
JCJim Chundevalelinaccidentalcomplexity.hashnode.dev·May 2 · 10 min readPart 7-What I Learned, What I'd Do DifferentlyWhat's Running Now The stack that is currently serving 100+ devices across my two networks: So far, everything is working as expected. Ads are blocked, DNS is encrypted and both networks have real c00
