Loading
3 minutesEvaluate prompts in the Anthropic Console
See the smallest no-code version of a repeatable prompt eval.
Watch nextTech With Tim. A tight, no-nonsense Ollama walkthrough — install, pull a model, chat, then poke at the local HTTP API from Python and create a custom model with a Modelfile. Covers exactly the workflow the article describes for daily use on a Mac, including how to think about model size vs. your machine's RAM.
Install commands and recommended model names change. Keep the local-first workflow, but check current Ollama model names, memory requirements and licensing before using any model on client or company data.
Install a local model runner, pull a small model and understand the privacy/performance tradeoff before using it for real work.
Comfort with a terminal and basic awareness that local models vary heavily by size, quantization and hardware.
Continue through the same learning path with the next curated companion videos.
