Hacker News new | ask | show | jobs
by jupr 14 days ago
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.
1 comments
JumpCrisscross 14 days ago
> I want claude power, in a box, at my house

This is still a six-figure commitment, possibly high five.

link
jupr 14 days ago
How do you know this and what does it really cost. Those numbers make no sense to me.
link
JumpCrisscross 14 days ago
> 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.

link
jupr 14 days ago
Wow these economics really make zero sense long term if they don't get more efficient.
link