Goal: wiring Hugging Face models into my local llm (Ollama) app, testing prompt-following, and seeing how far I can push a 12GB RTX 5070 before the system starts leaning hard on the CPU. The short version: it works, but only because the stack is allowed to spill parts of the model back to system memory. The current setup The image UI lives on my web server, but the GPU does not. The request path looks like this: ...
One of the simplest home server upgrades is running a VPN at home and connecting to it from your phone. If you have a static IP at home, or reliable dynamic DNS, this is not a big project anymore. WireGuard is the one I would set up today. OpenVPN is still fine too. Both have solid iPhone apps. The workflow is straightforward: make a client profile, import it on the phone, flip the switch, and your phone is effectively back on your home network. ...
I do all my development on a Linux box with no GPU. My RTX 5070 lives across the room in a Windows gaming machine. Rather than dual-booting or doing native Windows dev (no), I turned the gaming box into a headless Linux GPU server I can SSH into, and it still plays games. The setup ...