Small Language Models (SLMs) vs Large Language Models (LLMs)

Towards Efficient, Reliable, and Deployable Language Intelligence at the Edge Authors: Parth (Akshat Raj) — Draft for submission / public distribution Date: Feb 13, 2026 (Asia/Kolkata) Abstract The last five years have seen explosive progress in large language models (LLMs) — exemplified by systems such as ChatGPT and GPT-4 — which deliver broad capabilities but at heavy computational, latency, privacy, and cost budgets. In parallel, a renewed research and engineering focus on Small Language Models (SLMs) — compact, task-optimized models that run on-device or on constrained servers — has produced techniques and models that close much of the gap while enabling new applications (on-device inference, embedded robotics, low-cost production). This article/review compares SLMs and LLMs across design, training, deployment, and application dimensions; surveys core compression methods (distillation, quantization, parameter-efficient tuning); examines benchmarks and representative SLMs (e.g., Ti