Hacker News new | past | comments | ask | show | jobs | submit
technocratius | on: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows
Yeah but I presume this has more to do with latency than overall compute, right?
notnullorvoid | parent
Yes latency, and the usual preference of ownership over rentership. Similarly their are benefits to running local AI too, like data privacy and control.