AIXDAabout 2 hours ago
Local LLM in Proxmox home lab
1 min read
A home lab owner moved AI from cloud to a local LLM in Proxmox, using Lemonade Server in an LXC on a Ryzen AI Max+ 395. ROCm backend ran a 120B model at 19 tok/s versus 5 tok/s on Vulkan. The setup prioritizes readable and editable automation rules.
Level
Hype check
Tap to vote and see what everyone thinks.
Summary by ByteBrief
