DeepX claims inference up to 100B parameters at less than 5 W

Re:DeepX claims inference up to 100B parameters at less than... by dinfinity on Monday November 09, 2026 @04:25PM (#50432412)

Statements like these often overlook that a human brain is pretty slow for a lot of tasks. It's hard to make direct comparisons, but for language (related cognitive work) we're at maybe a few tokens per second.

I wonder how even a team of humans (a meat mixture of experts) would perform on the AI benchmarks, measured in energy use per intelligence index/benchmark point.

[ Parent | on HN ]

Re:DeepX claims inference up to 100B parameters at less than... by egberts1 on Monday November 09, 2026 @04:34PM (#50432536)

[delayed]

[ Parent | on HN ]

Re:DeepX claims inference up to 100B parameters at less than... by danuker on Monday November 09, 2026 @05:22PM (#50433128)

Back in July, I timed myself manually looking at some data files to create an index out of them, and out of curiosity asked some AI to do the same.

It took me an hour (61 minutes) and I made 4 mistakes in about 80 entries. It took DeepSeek-V4-Flash 3 minutes, it cost $0.034, and only made 2 mistakes. There is no contest. Humans have lost.

[ Parent | on HN ]

Re:DeepX claims inference up to 100B parameters at less than... by anonymous908213 on Monday November 09, 2026 @05:39PM (#50433292)

Uh, yeah, humans lost at data processing about halfway through the last century. The calculator can calculate fast than you. Great that you've finally discovered what computers can do, but it doesn't mean what you seem to think it means.

[ Parent | on HN ]

Re:DeepX claims inference up to 100B parameters at less than... by latentsea on Monday November 09, 2026 @06:41PM (#50433983)

These days I like to think of myself as a 100T dense model with 20 t/s prefill and 2 t/s decode. I am an RL(HF/VR/CR) policy rollout at this point.

[ Parent | on HN ]