Re:In first, California city overwhelmingly votes to permane...
by rvz on Thursday June 04, 2026 @09:40AM
(#48398518)
That's why Microsoft and all of the OEMs announced localized AI models that run on the new NVIDIA CPU on laptops.
[ Parent
| on HN ]
Re:In first, California city overwhelmingly votes to permane...
by jupr on Thursday June 04, 2026 @09:47AM
(#48398613)
I don't think these small models are really that powerful yet and I don't really like the direction of per device localized models baked in to the OS. To wimpy and untrustworthy.
I want claude power, in a box, at my house, for my entire family completely compartmentalized from my operating system.
Re:In first, California city overwhelmingly votes to permane...
by JumpCrisscross on Thursday June 04, 2026 @10:14AM
(#48398982)
> I want claude power, in a box, at my house
This is still a six-figure commitment, possibly high five.
Re:In first, California city overwhelmingly votes to permane...
by jupr on Thursday June 04, 2026 @12:46PM
(#48401236)
How do you know this and what does it really cost. Those numbers make no sense to me.
Re:In first, California city overwhelmingly votes to permane...
by JumpCrisscross on Thursday June 04, 2026 @01:23PM
(#48401735)
> How do you know this and what does it really cost
The cost of RAM and size of models. For Kimi K2.6 you need 2TB RAM. That’s $40k with DDR5. If you want it to run at the speeds you’re accustomed to with Claude, you need HBM memory, which costs more.
Practically speaking, you need to sink $250k+ into a 8x B200 node. So yeah, 6 figures to run properly. High 5 figures if you’re okay with really slow responses.