Date
Publisher
arXiv
The rapid global expansion of large language models (LLMs) has created new opportunities for personalised and inquiry-driven learning. However, most AI chatbot systems for education rely on continuous internet connectivity, cloud infrastructure, and modern hardware. These requirements reinforce digital inequalities and limit the practical deployment of AI-supported learning in bandwidth-constrained and resource-limited environments worldwide. This paper presents Arapai, an offline-first AI chatbot architecture designed to operate entirely without internet connectivity on low-specification, CPU-only devices. The system integrates locally hosted, quantised language models with automatic hardware-aware model selection and pedagogically tiered response control. By performing inference fully on-device and maintaining models resident in memory for performance optimisation, Arapai delivers curriculum-aligned explanations, structured problem-solving support, and differentiated instructional depth without reliance on cloud services. A pilot deployment in secondary and tertiary institutions operating under limited-connectivity conditions evaluated the system across four dimensions: technical performance, usability, perceived answer quality, and educational impact. Results indicate stable operation on legacy hardware, acceptable response times for standard instructional queries, and positive learner and teacher perceptions regarding self-directed learning support. Rather than replacing cloud-based AI systems, this work proposes a complementary deployment paradigm for infrastructure-constrained education systems. The study contributes a hardware-aware architectural framework for decentralised AI tutoring and highlights the role of offline-first design in advancing digital inclusion and infrastructure-resilient educational technology.
Study at a glance
- Question: Can an offline-first AI chatbot effectively support learning on low-specification devices without internet access?
- Setting and data: Secondary and tertiary institutions in limited-connectivity conditions; sample sizes and dates not stated in the abstract.
- Method: Pilot deployment and evaluation of a custom offline system
Why it matters
Most educational AI chatbots require continuous internet access, cloud infrastructure, and modern hardware. These requirements reinforce digital inequalities and prevent AI-supported learning from reaching resource-limited and bandwidth-constrained environments.
Key findings
- The offline system operated stably on legacy, low-specification hardware while achieving acceptable response times for standard instructional queries.
- Learners and teachers reported positive perceptions of the chatbot's ability to support self-directed learning.
- Fully on-device inference successfully delivered curriculum-aligned explanations, structured problem-solving help, and differentiated instructional depth without cloud access.
Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.
What is the application?
Who age?
Why use AI?
Study design
