Proxmox

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. ...

Moving virtual machines between Proxmox hosts is straightforward when you have a cluster configured, but what if you’re running standalone nodes? This guide walks through the process of migrating VMs between two independent Proxmox servers on the same network, without needing to set up clustering. [IMAGE: Diagram showing two Proxmox servers on a flat LAN with an arrow indicating VM migration between them] I recently needed to migrate several VMs from an older Proxmox host to a newer one with faster storage. Both systems were on the same network but not clustered, and I wanted to avoid the overhead of downloading backup files through the GUI. The solution? Streaming backups directly over SSH using Proxmox’s built-in vzdump tool. ...