Using an LLM to deploy an LLM on spare hardware (Homelab - Ep. 0x004)
Table of Contents
Description
I use Claude Code to deploy Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M and other models to computer built from spare hardware that was sitting unused.
Claude generated code: https://github.com/dev-dull/questionable_commands/tree/main/homelab/01082026-0x004-jalopy_llm
#ClaudeCode #LocalLLM #llamacpp #SelfHosted #AI #Qwen3 #nvidia #nvidia2080 #homelab