Three models one size class up — Qwen3-14B, Phi-4, and Mistral-Small-24B at Q4_K_M quantization — measured on the same 1,505-sentence limitation gold set, same prompt, same harness as the earlier six-model comparison. Qwen3-14B scores F1 0.8272 as a single model, above the previous two-model union (0.8143) and the published rule-system reference (0.800). VRAM at load: 10.6 GB of 16.3 GB. Every number is a full-split measurement.
Scientific papers state their own defeats in words: a sample that could not be enrolled, a computation that could not be afforded, data that could not be obtained. A phrase list finds those statements with precision 0.23. Judging each match in context — with rules, two trained classifiers, and a pair of 8-billion-parameter models on two 16GB GPUs — raises the measured operating point to a 0.945-precision auto-admit gate and a two-judge F1 of 0.814, beating the published rule-based reference on the same gold set. Every number is a full-split measurement.
Forty-three scanned medical sheets, understood by a 3-billion-parameter model running on an on-premise 4080 GPU, turned into 208 searchable vectors and 45 tracked lab values — in eleven minutes, with nothing sent to the cloud. The pipeline, the timings, and the numbers.