News for hackers. Stuff that matters.

A comment on MAI-Code-1-Flash. Parent comment

Re:MAI-Code-1-Flash by Flere-Imsaho on Tuesday June 02, 2026 @03:37PM (#48375158)
Yeah the future is probably a number of highly specialised small models you can run on your own hardware rather than massive frontier models in the cloud.

That's what I'm betting on anyway.

[ Parent | on HN ]
Re:MAI-Code-1-Flash by thewebguyd on Tuesday June 02, 2026 @03:43PM (#48375221)
That seems to be what Microsoft is betting on also based on what was shown at the BUILD keynote today + that new surface ultra and the surface mini PC with the new Nvidia chip. Nadella really played up local AI as the main use case they have in mind.
[ Parent | on HN ]
Re:MAI-Code-1-Flash by search_facility on Tuesday June 02, 2026 @03:49PM (#48375302)
MOE basically work that way already, QWEN/etc with low active params (A-number in name) allows to inference big models locally (only active params have to fit into memory)
[ Parent | on HN ]
Re:MAI-Code-1-Flash by girvo on Tuesday June 02, 2026 @06:11PM (#48377038)
Step 3.7 Flash on my Asus GB10 based mini pc is incredibly close to that today. I’m very impressed, and that’s without MTP to boost performance
[ Parent | on HN ]