Use LLMs like Llama 4, Gemma 3, and DeepSeek locally and control your data. Set up your own offline AI lab with an NVIDIA A4000 GPU wired to a NixOS VM via PCIe passthrough, set up Ollama and Open WebUI, and get chatting with local LLMs all entirely within your tailnet.

Tailscale is a platform providing secure networking solutions for teams and businesses. Readers can learn about VPN technology, network security, and remote access solutions. With articles, tutorials, and case studies, Tailscale offers  insights and expertise for implementing secure networking infrastructure and protecting sensitive data.

Tailscale

A comprehensive guide to building a private AI infrastructure using local hardware. The setup involves configuring Proxmox virtualization with GPU passthrough, deploying NixOS VMs with Docker and NVIDIA drivers, and running Ollama with Open WebUI for local LLM access. Tailscale provides secure remote access to the AI stack from any device. The approach eliminates monthly subscription costs and keeps all data private while offering ChatGPT-like functionality through self-hosted models like Llama 4, Gemma 3, and DeepSeek.

Self-host a local AI stack and access it from anywhere