YouTip

# Ollama Tutorial !(#) Ollama is an open-source local large language model running framework, designed for convenient deployment and running of Large Language Models (LLM) on local machines. Ollama supports multiple operating systems, including macOS, Windows, Linux, and running via Docker containers. Ollama provides support for model quantization, which can significantly reduce VRAM requirements, making it possible to run large models on ordinary home computers. * * * ## Who is this tutorial for? Ollama is suitable for developers, researchers, and users with high data privacy requirements. It can help users quickly deploy and run large language models in a local environment while providing flexible customization options. Using Ollama, we can run Llama 3.3, DeepSeek-R1, Phi-4, Mistral, Gemma 2, and other models locally. * * * ## What you need to know before learning this tutorial This tutorial is suitable for developers with Python basics. If you are not familiar with Python, you can refer to [Python 3.x Basic Tutorial](#). Understand the difference between Docker images and containers, know how to pull images from Docker Hub and run containers. For Docker-related content, see: (#). Be familiar with basic operations of command-line tools (such as terminal or command prompt), such as creating, deleting, and moving files and directories, as well as how to run scripts and programs. * * * ## Create a new model We can use the ollama create command to create a model from Modelfile: ## Example ollama create model -of ./Modelfile * * * ## Related Links Ollama Official Website: [https://ollama.com/](https://ollama.com/) Github Open Source Address: [