Insights
Observations, experiences, recommendations from our work with AI, Local AI and software development. No hype lists, no PR — just what helps.
-
Goodbye cloud, hello sovereignty: the technology behind local AI
Miniaturization, inference engines and the memory bottleneck — a technical overview
Why large language models can now run on hardware you own: pruning, quantization, distillation — and unified memory as the answer to the real bottleneck.
Read → -
The rzfz.ai Stack: local matters
Five ways local AI is changing how we build and test software
Why unified-memory hardware plus open models finally makes sense right now — and five concrete ways we use the rzfz.ai Stack for development and testing.
Read → -
AI pair-programming in 2026: what has changed
A year of Claude/Cursor/Copilot on the team — taking stock
How our practice has shifted since early 2025: tool selection, test discipline, agent code review.
Read → -
Local AI: why 2026 is the year
Open-source models, Strix Halo, GDPR — the stars align
Three reasons why now is the right moment to run AI workloads in your own premises.
Read →