A Hybrid Lightweight LLM Chatbot for Sustainable Cryptocurrency Investment Decisions: Optimizing Small Models for Domain-Specific Performance

Abstract

This paper presents a hybrid chatbot for sustainable cryptocurrency investment, powered by small-scale Large Language Models (LLMs). We evaluate the performance of various lightweight LLMs (under 10B parameters) on blockchain and sustainability-related tasks, demonstrating that carefully orchestrated smaller models can effectively match or exceed the performance of larger models in domain-specific applications. Our multi-agent Retrieval-Augmented Generation (RAG) pipeline, incorporating real-time sustainability metrics from the Crypto Carbon Ratings Institute, achieved 87.09% accuracy in providing investment guidance, improving upon the 72.58% baseline of individual models. The results show that refined instruction engineering and specialized pipeline architecture can significantly enhance model performance without requiring larger, more energy-intensive models. This work contributes to both the practical implementation of sustainable cryptocurrency investment tools and the broader discussion of environmental considerations in AI system design and deployment.