ollama/ollama

Ollama provides a framework for running and managing local machine learning models. It includes a command-line interface for model lifecycle management, such as creation, embedding generation, and configuration, alongside a stable API for programmatic interaction across multiple programming languages.

The platform supports the import of models and adapters in various formats, including GGUF and Safetensors. Users can define custom model behaviors, prompt templates, and system messages through a configuration file format. It also offers tools for fine-tuning models with LoRA adapters and applying quantization to manage memory usage and inference performance.

The software includes infrastructure for cross-platform builds, hardware acceleration for specific graphics processing units, and system-level service management. Installation is supported through automated scripts, and the environment provides utilities for monitoring runtime logs and testing core functionality.