Deploying Large Language Models (LLMs) with Ollama

Short summary

A practical guide to installing and running large language models locally with Ollama on Linux, macOS, and Windows. Covers pulling models like Llama 3.3, DeepSeek R1, and Mistral, running interactive prompts, managing model lifecycle, and configuring environment variables for GPU support and network exposure. Includes systemd setup and optional AMD ROCm instructions.

• •Install Ollama via official script and pull models like Llama 3.3, DeepSeek R1, and Mistral
• •Run interactive prompts and compare model quality and speed on local hardware
• •Configure environment variables for GPU support, network exposure, and memory management

Generated with AI, which can make mistakes.