J. Sciammarelli

Empirical Analysis of Small Language Model Quantization for CPU-Only Cloud Infrastructure

As Large Language Models (LLMs) grow in complexity, the hardware required to serve them often exceeds the capabilities of standard cloud instances and edge devices. This article investigates the efficacy of Small Language Models (SLMs) specifically Llama 3.2 (1B) and Qwen 2.5 (1.5B) as cost-effective alternatives when...