Luna finished a neural rendering client job using just 6-7% of quota

MickeySteamboat · x · 2026-09-30

The author reports that Luna at 'extra high' setting completed a neural rendering client project using only 6-7% of the quota, even with other priority kernel work running in the background — a notable data point on agent subscription efficiency.

Original post →

More from coding & agent

coding & agent channel →