All posts
Eco AI5 min read

A living-room iMac. Not a cluster.

We keep the green claim modest because most AI energy numbers are difficult to prove. What we can say: cognira Retrain 12B serves from one 16GB iMac, answers are bounded, and background learning yields whenever someone is waiting on a reply.

§ 01

Efficiency we can measure

One 16GB serving machine instead of a GPU cluster. Short-answer token ceilings avoid waste. Repetition guards stop runaway output. We will not publish a carbon number until we can meter it at the wall.

The greenest token is the one we never need to generate. Efficiency starts with useful answers, not a poster of invented tonnes.

§ 02

When the iMac is quiet, it reviews

Eligible examples wait in a guarded queue. Training starts only after there is enough clean material and serving is idle. The result is a candidate, not an automatic live update.

  • Signal. Only safe, useful, short replies survive. Down-rated and contaminated replies stay out.
  • Schedule. Background work waits for the iMac to be idle so live chat keeps priority.
  • Promotion. A candidate must load and pass its checks before anything live can change.

Live chat first. Learning second.

§ 03

Local, if you want zero cloud

cognira Entity runs the same loop on your hardware — local model, local memory, optional weight retraining — with nothing leaving the machine. Early access for Pro and Max.