Private, Local AI, Made Quick and Simple | Llama Cpp + Qwen3.6 35B MoE

Timestamps in pinned comment!!! This video is for demonstrating how quickly someone can get up and running with a local LLM using Llama cpp as a low overhead inference engine, now has a web ui option. Quickly demonstrating a simple tool call (Running a Command on your machine, not just a chat interface!) I hope someone can find this helpful. Building and customizing agents, skills, etc. is in the works. Feel free to comment what you'd want AI to do, or any requests. Thank you!