Re:Every AI Subscription Is a Ticking Time Bomb for Enterprise
by throw1234567891 on Sunday May 17, 2026 @11:21AM
(#48169721)
Or a single mlx cluster if one can find second hand machines somewhere. Difficult to get your hands on today, certainly, but not impossible.
Re:Every AI Subscription Is a Ticking Time Bomb for Enterprise
by snovv_crash on Sunday May 17, 2026 @01:33PM
(#48171063)
Qwen 3.6 27b is somewhere around Opus 4. It runs on a 5090, a $2k desktop GPU, at reasonable speeds.
Eventually, we'll see. Frontier models still need some pretty serious hardware which will slowly come down in cost. Smaller models are becoming more capable, which will presumably continue to improve.
I think there's still a pretty big gap, though. Claude estimates Opus 4.6 and GLM-5 need about 1.5Ti VRAM. It puts gpt-5.5 around 3-6Ti of VRAM.
That's 8x Nvidia H200 @ ~$30k USD each. Still need some big efficiency improvements and big hardware cost reduction.