Re:Flash-Moe: Running a 397B Parameter Model on a Mac with 4...
by hrmtst93837 on Sunday March 22, 2026 @08:38AM
(#47476897)
If you want decent throughput and do not care about burning SSD write cycles on a box that was never meant to act like a tiny inference server, a used server with actual RAM is still the cheaper and less silly option. I woudn't expect Apple's warranty team to be much help.
[ Parent
| on HN ]