Tutorials.pro

Short, working tutorials on running AI locally, evaluating models honestly, and shipping agent workflows. No listicles, no filler — every page is something we actually run.

Tutorials

Running a Useful Local LLM on Consumer Hardware

What actually fits in RAM, what quantization does to quality, and how to pick a model you can serve on a CPU-only box without burning a weekend.

Local inference · ~12 min read
How to Evaluate LLM Claims Before You Believe the Benchmark

Vendor benchmarks, latency numbers, and "100x faster" claims — a field guide to testing them yourself in an afternoon.

Evaluation · ~10 min read
Agent Workflows That Survive Contact With Reality

Where multi-agent setups actually pay off, where they collapse, and the verification habits that keep them honest.

Agents · ~14 min read

What this site is not

Not a content farm. Not programmatic SEO pages. Not beauty, lifestyle, or make-up tutorials — the name is generic, so we keep the niche narrow and the writing real. New tutorials are added when there is something tested worth teaching.