Tools tested, numbers shown
LLMs, APIs, hardware and measurement tools. Every page states whether the evidence is research, hands-on use or a published benchmark.
All product reviews
- Best mini PC for a useful local LLM? Start with memory — A practical reading of the 2024 M4 Mac mini for local models, including memory tiers, model-weight arithmetic and the evidence still missing. (research, 2 min)
- The cheapest API for structured extraction — A dated cost comparison for turning 1,000 documents into JSON, with input, output and local-compute arithmetic shown. (research, 2 min)
- Claude vs ChatGPT for working through a real codebase — A decision framework for choosing between Claude and ChatGPT for repository work, with workflow, privacy and cost questions separated from model hype. (research, 2 min)
- Local vs hosted LLMs for private documents — How to choose a local or hosted model for sensitive documents by threat model, retention, capability and operating cost—not by slogans. (research, 2 min)
- Power meters for local AI: is the Tapo P110M accurate enough? — What the Tapo P110M can and cannot tell you about local-AI energy use, with resolution, sampling and a repeatable measurement protocol. (research, 2 min)