I'm Not Convinced the AI Bubble Exists

Re:I'm Not Convinced the AI Bubble Exists by somenameforme on Monday November 09, 2026 @08:10AM (#50425108)

Here [1] are some various benchmarks for a RTX 4090 on models like Qwen 3.8, where it usually hits around 43 tokens/s. You can find similar vids on YouTube showing it live for comparison, 'proof' if you doubt, etc. And yes, it is frontier tier.

[1] - https://getrigbase.com/gpus/rtx-4090/

[ Parent | on HN ]

Re:I'm Not Convinced the AI Bubble Exists by xvector on Monday November 09, 2026 @11:13AM (#50427544)

Dude, why do you think I care about benchmarks on a 4090 when I know for a fact my 6000 Blackwells are insufficient?

[ Parent | on HN ]

Re:I'm Not Convinced the AI Bubble Exists by somenameforme on Monday November 09, 2026 @09:59PM (#50435541)

If you're doing less with more then I'd imagine you'd certainly care, because that means the problem is you, and not your hardware.

[ Parent | on HN ]

Re:I'm Not Convinced the AI Bubble Exists by xvector on Tuesday November 10, 2026 @09:54AM (#50441244)

The problem is that open models are benchmaxxed and are fairly useless on hardware of this size.

[ Parent | on HN ]