Joseph Walusimbi, Ann Move Oguti, Joshua Benjamin Ssentongo et al.
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.