Edge-native Small Language Models for 6G Intent-driven Slicing: A Hardware-grounded Empirical Study
This study presents a deterministic, hardware-grounded empirical evaluation of open-weight Small Language Models (SLMs) on CPU-only edge infrastructure.Using greedy decoding for exact reproducibility, we benchmark four ∼8B-parameter families (Llama 3.1, Qwen 2.5, Gemma 2, GLM-4) under identical Q4_K_M quantisation, the...