Ollama

Run large language models locally for private, customizable AI interactions. Ollama is the easiest way to automate your work using open models, while keeping your data safe. Ollama is a framework for running large language models locally, ensuring privacy and customization. It supports macOS, Linux, and Windows (preview), with GPU acceleration for NVIDIA/AMD. Larger models require at least 16GB RAM and a compatible GPU for optimal performance. It runs models locally, requiring no internet after model download. Models like Llama 3.3, Mistral, Gemma 3, and DeepSeek-R1 are supported. Ollama is CLI-based but integrates with GUIs like Open WebUI for easier use.