Short records of what I tried in the homelab, what worked, and what didn't.https://lxkapp.com/https://lxkapp.com/notes/local-llm-inference/https://lxkapp.com/notes/local-llm-inference/One Qwen3.6 35B A3B serving both the assistant and bulk enrichment on two consumer GPUs: what fits, why the logs lie about which model ran, and the thinking-mode setting that returned empty responses.Thu, 27 Aug 2026 00:00:00 GMThttps://lxkapp.com/notes/hybrid-retrieval-globirie/https://lxkapp.com/notes/hybrid-retrieval-globirie/Where Globirie's lexical and dense retrieval actually stand, the pgvector filter trap, and why the reranking window matters more than candidate depth.Wed, 01 Jul 2026 00:00:00 GMT