PN — Evaluated model: qwen2.5:7b
qwen2.5:7b — family Qwen 2.5 (Alibaba), GGUF Q4_K_M, run locally via Ollama (seed=42, temp=0.0). Phase-B results: triage F1-macro 0.4791557070611423, estimation MAE 1.86 SP, prioritization accuracy 0.42 (N=100 each). Best estimation model overall (MAE 1.86 SP).
Source: PUMA project documentation + raw benchmark results · Traceability: ANXAG-015,PUMA-023 · Confidence: verified-at-primary-source