Re:Every AI Subscription Is a Ticking Time Bomb for Enterprise
by dools on Sunday May 17, 2026 @12:28PM
(#48170398)
Kimi k2.6 is about on par with GPT 5.2 so I’d say open weight models are about 6 months behind.
[ Parent
| on HN ]
Re:Every AI Subscription Is a Ticking Time Bomb for Enterprise
by cbg0 on Sunday May 17, 2026 @12:57PM
(#48170679)
The Q4 quantization requires about 600GB of RAM without context, not exactly consumer hardware friendly.
Re:Every AI Subscription Is a Ticking Time Bomb for Enterprise
by janderland on Sunday May 17, 2026 @12:54PM
(#48170653)
Has Kimi found a way to vastly reduce the amount of VRAM required without running at 3 tokens per second? That’s the real concern.