←back to thread

News: Arm announces next Generation core family called Arm Lumex

(www.phoronix.com)
37 points HeyMeco | 1 comments | 10 Sep 25 07:20 UTC | HN request time: 0.203s | source
Show context
avhception ◴[10 Sep 25 09:49 UTC] No.45195415[source]▶
What exactly is this on-device AI stuff that everybody is talking about? I'm a mere Sysadmin, so probably I'm missing something here.

The last time I tried to run local LLMs via my 7900XT using LMStudio, even with 20gb of VRAM, they were borderline usable. Fast enough, but quality of the answers and generated code was complete and utter crap. Not even in the same ballpark as ClaudeCode or GPT4/5. I'd love to run some kind of supercharged commandline-completion on there, though.

Edit: I guess my question is: What exactly justifies the extra transistors that ARM here and also AMD with their "AI MAX" keep stuffing onto their chips?

replies(2): >>45195468 #>>45195792 #
1. theuppermiddle ◴[10 Sep 25 09:58 UTC] No.45195468[source]▶
I guess AI is not just LLM. Image processing, speech to text etc would fall under the use case. Regarding GenAI, Pixel phones already run nano model on the phone with decent performance and utility.