Artificial intelligence (AI) and large language models (LLMs) are transforming educational technology by enabling conversational tutoring, personalized explanations, and inquiry-driven learning. However, most AI-based learning systems rely on continuous internet connectivity and cloud-based computation, limiting their use in bandwidth-constrained environments. This paper presents an offline-first large language model architecture designed for AI-assisted learning in low-connectivity settings. The system performs all inference locally using quantized language models and incorporates hardware-aware model selection to enable deployment on low-specification CPU-only devices. By removing dependence on cloud infrastructure, the system provides curriculum-aligned explanations and structured academic support through natural-language interaction. To support learners at different educational stages, the system includes adaptive response levels that generate explanations at varying levels of complexity: Simple English, Lower Secondary, Upper Secondary, and Technical. This allows explanations to be adjusted to student ability, improving clarity and understanding of academic concepts. The system was deployed in selected secondary and tertiary institutions under limited-connectivity conditions and evaluated across technical performance, usability, perceived response quality, and educational impact. Results show stable operation on legacy hardware, acceptable response times, and positive user perceptions regarding support for self-directed learning. These findings demonstrate the feasibility of offline large language model deployment for AI-assisted education in low-connectivity environments.

翻译：人工智能（AI）与大语言模型（LLM）正通过实现对话式辅导、个性化解释及探究驱动式学习，推动教育技术变革。然而，多数AI学习系统依赖持续网络连接与云端计算，限制了其在带宽受限环境中的应用。本文提出一种面向低连接场景下AI辅助学习的离线优先大语言模型架构。该系统通过量化语言模型实现全本地推理，并采用硬件感知模型选择机制，使其可部署于仅搭载低规格CPU的设备。通过消除对云基础设施的依赖，系统能够通过自然语言交互提供符合课程标准的解释与结构化学术支持。为适配不同教育阶段学习者的需求，系统引入自适应响应层级机制，可生成四种复杂度等级的解答：简易英语、初中层次、高中层次及专业层次。这使得解释内容可依据学生能力动态调整，从而提升学术概念阐释的清晰度与可理解性。系统已在有限连接条件下的部分中学及高等院校完成部署，并从技术性能、可用性、感知响应质量及教育影响四个维度展开评估。结果显示，系统在老旧硬件上运行稳定，响应时间合理，用户对自主学习支持能力给予积极反馈。这些成果证明了在低连接环境中部署离线大语言模型进行AI辅助教育的可行性。