@CassieFox23

How to run REA with local models on a single 12 GB GPU, and how five models compared.

Start-up timings of REA on Node 22, 24 and 26 on Linux, plus a comparison of five local models.

Practical setup notes for running REA on Fedora-based Linux, with the problems hit along the way and a queue of tests.

Asks REA which function prints one message in a stripped, optimised bzip2 binary; the answer and 24 callees matched an unstripped build and the source, and the post lists what this does not prove.