27B model with skills layer handles regulated data workflows locally
Ubunta · x · 2026-08-29
- Experiment: Tested if adding skills to a small 27B model could handle regulated data workflows instead of moving to a larger model.
- Setup: 27B dense model (Q6), 2 consumer GPUs, fully local, no fine-tuning.
- Implementation: 5 skill MD files (cohort specs, value sets, index/washout logic, bias review, ledger classification), constrained JSON output. All codes, counts, and numbers come from tool calls, not the model.
- Findings: Most improvements came from the skill and context layer. Main issue is loading the wrong skill. Adding skills may be sufficient for many tasks before scaling up.
Related event: 27B Model with Skill Layer Handles Regulated Healthcare Workflows Locally(2 posts)→
More from coding & agent
- User complains about Claude's heavy reliance on shell commands — weswinder · 2026-08-29
- Google Cloud proposes a 5-layer architecture for resilient production-grade agents — rseroter · 2026-08-29
- Nvidia releases Nemotron 3.5 Lightning, an open model optimized for always-on agents — nvidia · 2026-08-29
- GLM-5.3 open weights released; Unsloth enables local run with 83% size reduction — danielhanchen · 2026-08-29
- Unify CTO breaks down cutting agent costs 95% before launch — brandon_galang · 2026-08-29
- Lean4 Formal Verification: Ensuring correctness in the age of AI agents — AI Engineer · 2026-08-29