Your first local LLM, start to finish
Install Ollama, pull Llama 3.2 3B, chat with it, hit its API, and fix the five things that break on a first install. You finish with a working local LLM.
Blog
Engineering
Posts on AI engineering, LLM systems, and software development.
System requirements by OS for local LLMs
What macOS, Linux, and Windows each need before you run a local LLM in 2026. Mac is the smoothest, Linux gives you the most knobs, and native Windows finally just works.
Install the OpenAI SDK
Install the OpenAI SDK for Python and Node, set your API key, and prove it works with a one-line chat call.
Install the Anthropic SDK
Install the official Claude SDK for Python and Node, set your API key the safe way, and prove it works with a one-line call.
Install LM Studio
Install LM Studio on macOS, Linux, and Windows, then flip on the local OpenAI-compatible server so any client library can talk to a model on your own machine.
Install llama.cpp
Build llama.cpp from source with Metal or CUDA, then run a GGUF model with llama-cli. The closest thing to bare-metal local inference.
Install Ollama
Get Ollama running on macOS, Linux, or Windows, pull your first model, and confirm it works with ollama list. The shortest path to a local LLM.
Install Docker
Get Docker running on macOS, Linux, or Windows, confirm it with hello-world, and dodge the licensing and resource traps that trip people up.
Install Python the right way, with uv
Leave system Python alone. Install uv, then let it handle Python versions and per-project virtual envs from one fast binary.
Install Node.js and npm without future regret
Install Node and npm through a version manager so you can switch versions per project. fnm is my pick, with nvm and Volta as alternatives.
Install Git
Install Git on macOS, Linux, and Windows, set your name and email so commits get attributed to you, and confirm it all worked in one command.
Install Homebrew
The one-line Homebrew installer for macOS, Linux, and WSL, plus the PATH step Apple Silicon needs and a quick way to check it actually took.