Large language models work well because they’re so large. Large language models (LLMs) also require considerable computational power each time they answer a request, which makes them notorious energy hogs. IBM, Google, Microsoft, and OpenAI have all recently released small language models (SLMs) that use a few billion parameters—a fraction of their LLM counterparts. He called the method “optimal brain damage.” Pruning can help researchers fine-tune a small language model for a particular task or environment. For researchers interested in how language models do the things they do, smaller models offer an inexpensive way to test novel ideas.