Hacker News new | past | comments | ask | show | jobs | submit
notnullorvoid | on: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows
You can find it today for gaming. Even despite the outlandish rise in hardware costs, there is very little demand for cloud gaming.
technocratius | parent | next
Yeah but I presume this has more to do with latency than overall compute, right?
notnullorvoid | root | 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.
| parent
{"deleted":true,"id":49250529,"parent":49248095,"time":1786399906,"type":"comment"}