Evaluating Financial LLM Architectures on Consumer GPUs: Model Comparison and Temperature-Based Hyperparameter Tuning

Kavdir, Bugra (2025) Evaluating Financial LLM Architectures on Consumer GPUs: Model Comparison and Temperature-Based Hyperparameter Tuning. Masters thesis, Dublin, National College of Ireland.

Preview

PDF (Master of Science) Download (1MB) | Preview

Abstract

This thesis investigates whether quantized, domain-specific Large Language Models (LLMs) deployed on consumer-grade hardware can generate profitable trading signals through technical analysis of cryptocurrency markets. We evaluate three models (Finance-LLM-13B, Finance-Llama-8B, and Phi-4) across 45 backtests spanning 15 sessions with heterogeneous hyperparameter configurations on Bitcoin/USDT 5-minute candles from November 2025. Finance-LLM-13B consistently achieves profitability against a -9.04% market baseline. We conduct controlled experiments isolating the effects of temperature and nucleus sampling (top-p) on trading signal quality. Critically, we demonstrate that domain-specific fine-tuning dominates model parameter scaling. Temperature-driven exploration benefits well-trained models but degrades weak models. Results emphasize that domain-specific training, rather than scale or sophisticated decoding strategies, is the dominant performance driver for financial reasoning. This work provides proof-of-concept evidence that LLM-based trading on consumer hardware is feasible, while establishing necessary conditions for robustness: multi-period validation and live-market validation before production deployment.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Vamadevan, Arundev UNSPECIFIED
Subjects:	H Social Sciences > HG Finance Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing
Divisions:	School of Computing > Master of Science in Artificial Intelligence
Depositing User:	Ciara O'Brien
Date Deposited:	02 Sep 2026 09:55
Last Modified:	02 Sep 2026 09:55
URI:	https://norma.ncirl.ie/id/eprint/9760

Actions (login required)

View Item