News for hackers. Stuff that matters.
Re:Token growth indicates future AI spend per dev by hoppp on Monday August 11, 2025 @02:35PM (#44867766)
I am looking forward for the AMD 395 max+ PCs to come down in price.

The inference speed locally will be acceptable in 5-10 years thanks to those generation of chips and finally we can have good local AI apps.

Re:Token growth indicates future AI spend per dev by bn-l on Monday August 11, 2025 @10:04PM (#44871545)
They don’t have the memory bandwidth
Re:Token growth indicates future AI spend per dev by hoppp on Tuesday August 12, 2025 @09:49AM (#44876164)
256 GB/s memory bandwidth is low but it still does around 40 tokens per sec with gpt-oss, good enough for local apps