News for hackers. Stuff that matters.

A comment on PaliGemma: Open-Source Multimodal Model by Google. Parent comment

Re:PaliGemma: Open-Source Multimodal Model by Google by simonw on Wednesday May 15, 2024 @08:50PM (#40374097)
I don't get it.

The iPhone does have a GPU, and it can be used to accelerate AI workloads.

This isn't theoretical. You can see this for yourself by installing https://apps.apple.com/us/app/mlc-chat/id6448482937 and turning off your wifi and running the quite capable Mistral 7B Instruct LLM on your phone.

I've even used it to answer simple questions while I was offline and only had my phone with me.

What am I missing here?

[ Parent | on HN ]
Re:PaliGemma: Open-Source Multimodal Model by Google by resource_waste on Thursday May 16, 2024 @08:36AM (#40377573)
What like 50 token responses?

Buddy I'm cranking out 4k.

Also LOL at the GPU thing. Its insane how well Apple marketing worked.

[ Parent | on HN ]
Re:PaliGemma: Open-Source Multimodal Model by Google by simonw on Thursday May 16, 2024 @08:49AM (#40377718)
I didn't say an iPhone was as good as a desktop with a dedicated graphics card. I said that an iPhone has a GPU and is capable of running a small but capable LLM.

Most people don't know that's possible yet.

Why do keep indicating that iPhones don't have a GPU?

[ Parent | on HN ]