To address the scalability of feedback in computer science while mitigating the privacy and cost limitations of commercial Large Language Models (LLMs), this study evaluates a locally hosted Small Language Model (SLM). We deployed a quantized Llama-3.1, GPT-4, and human instructors across introductory programming (N=176), operating systems (N=80), and a writing seminar (N=7). Mixed-methods analysis of student perceptions reveals that while the local SLM matched commercial LLMs and was rated higher by students for readability and actionability in technical courses, human feedback remained more favoured for highly specialized writing tasks. We demonstrate that local SLMs offer a privacy-preserving, zero-marginal-cost alternative for foundational feedback, supporting a tiered pedagogical framework where AI handles structural guidance while instructors focus on high-level conceptual scaffolding.

翻译：为解决计算机科学中反馈的可扩展性问题，同时规避商用大型语言模型（LLMs）的隐私与成本限制，本研究评估了一种本地部署的小型语言模型（SLM）。我们在入门编程（N=176）、操作系统（N=80）及写作研讨课（N=7）中部署了量化版Llama-3.1、GPT-4及人类讲师。基于混合方法的学生感知分析表明：在技术类课程中，本地SLM虽与商用LLMs表现相当，且学生在可读性与可操作性方面对其评分更高，但人类反馈在高度专业化的写作任务中仍更受青睐。本研究证明，本地SLM可为基础性反馈提供一种隐私保护且零边际成本的替代方案，支撑分层教学框架——由人工智能处理结构指导，而讲师聚焦高层面概念搭建。