# Local and small models

# Local and small models

Edward deploys on-premises and local large-language models, including NVIDIA Nemotron, using privacy-first architectures. He trains small models for targeted tasks; his deepest technical claim is applied small-model training, not machine-learning research.

For a mid-size accountancy firm, Edward trained a small model for document-specific extraction and categorization. It reduced manual effort by approximately 80%.