Diagram of a Proxmox host with a GPU-backed Ollama container, Open WebUI, a dev VM and Home Assistant

Local AI on Proxmox: The Complete Homelab Guide (2026)

Everything AI-related on this site runs on one Proxmox host in a cupboard. A GPU in an LXC container serves Ollama, a web front end sits on a VM next to it, Home Assistant talks to local speech models for voice, and my coding agents work from an always-on VM that I reach over Tailscale. None of it costs per token, none of it leaves the house, and the whole stack has survived every host reboot since I built it. ...

November 10, 2026 · 11 min · Tom Cocking
Terminal panel showing the environment variables for pointing Claude Code at Ollama and a results table for three local models on two coding tasks

Claude Code with a Local Ollama Model: Setup, and What a 12 GB GPU Can Do

Claude Code speaks the Anthropic API. Ollama now speaks it too. Point one at the other with three environment variables and Claude Code runs against a model on your own GPU. No API key, no per-token bill, and the prompts stay on your network. Whether it’s any good is a different question. I ran it against three models on an RTX 3060 with two small coding tasks each. One model did well at both. One was the best at one and the worst at the other. Treat what follows as a smoke test, not a benchmark, but the differences were big enough to matter. ...

November 6, 2026 · 8 min · Tom Cocking
Home Assistant Assist dialog on the Local LLM assistant: the user says it's too dark in the living room and the reply says it turned on the Living Room RGBWW Lights

Home Assistant Conversation Agent with a Local Ollama Model: Which Model Works

Home Assistant’s own Assist can already turn a light on. It matches your sentence against a list of templates and runs the one that fits. Say something it has no template for and you get “Sorry, I couldn’t understand that”. Point Assist at an LLM and that stops being true. “It’s too dark in the living room” works. The catch is that the model has to call Home Assistant’s tools correctly, and plenty of local models can’t. I ran three models against the same 18 commands to see which ones can. ...

November 3, 2026 · 9 min · Tom Cocking
Terminal showing Pi Agent startup with skills and extensions loaded

Understanding Pi Agent's Extension Model: Context Files, Skills, and TypeScript Extensions

If like me, you’re spending an increasing amount of time learning Pi Agent - the minimal terminal coding harness - you’ll quickly hit the point where you want to bend it to your workflow. There are four different mechanisms for doing that: context files, prompt templates, skills, and TypeScript extensions. They look similar on the surface but they operate at completely different layers, and picking the wrong one means either burning context unnecessarily or writing TypeScript when a Markdown file would have done the job. ...

May 19, 2026 · 10 min · Tom Cocking

Running Ollama in a Proxmox LXC with NVIDIA GPU Passthrough

Running large language models locally is genuinely useful — no API costs, no rate limits, and your data stays on your own hardware. The catch is getting GPU acceleration working inside a Proxmox LXC container, which involves a few non-obvious steps around driver installation and cgroup device passthrough. Why LXC and not a VM? VM GPU passthrough wasn’t an option here — no iGPU meant the host would have had no display output once the card was handed off. LXC was the practical solution, and it turns out to be a good one anyway: containers share the host kernel directly, so the GPU stays bound to the host’s NVIDIA driver and the container accesses it via bind-mounted device nodes and cgroup permissions. On top of that, LXCs are lighter weight than VMs, with less overhead and near-instant startup times. For a dedicated service like Ollama, it’s a solid fit. ...

March 22, 2026 · 11 min · Tom Cocking