LLM (Large Language Model)

A Large Language Model is a neural network trained on large text corpora to predict token sequences. Current models such as Claude, GPT, Gemini, and Llama are capable at code generation, reasoning, and tool use. Frontier models are usually accessed through a vendor's cloud API, which an air-gapped or offline environment cannot reach. Open-weight models such as Llama, Mistral, DeepSeek, and Qwen can run on local or on-premise hardware, keeping data inside the environment.