News for hackers. Stuff that matters.

A comment on A 30B Qwen Model Walks into a Raspberry Pi and Runs in Real Time. Parent comment

Re:A 30B Qwen Model Walks into a Raspberry Pi and Runs in Re... by empiko on Wednesday January 07, 2026 @01:39AM (#46523306)
The sota chatbots are getting more and more functionality that is not just LLM inference. They can search the web, process files, integrate with other apps. I think that's why most people will consider local LLMs to be insufficient very soon.
[ Parent | on HN ]
Re:A 30B Qwen Model Walks into a Raspberry Pi and Runs in Re... by woooooo on Wednesday January 07, 2026 @02:23AM (#46523549)
But that's just software that also runs fine locally. A few tools with a local LLM can do it.
[ Parent | on HN ]
Re:A 30B Qwen Model Walks into a Raspberry Pi and Runs in Re... by empiko on Wednesday January 07, 2026 @05:06PM (#46533757)
Well I don't see people running their web search locally, so I don't think they will run their own search+LLM.
[ Parent | on HN ]
Re:A 30B Qwen Model Walks into a Raspberry Pi and Runs in Re... by woooooo on Thursday January 08, 2026 @12:32AM (#46537573)
No but you can call out to Google or DDG APIs.
[ Parent | on HN ]
Re:A 30B Qwen Model Walks into a Raspberry Pi and Runs in Re... by BoxOfRain on Wednesday January 07, 2026 @07:23AM (#46525578)
Nah I disagree, tool calling isn't that difficult. I've got my own Cats Effect based model orchestration project I'm working on, and while it's not 100% yet I can do web browse, web search, memory search (this one is cool), and others on my own hardware.
[ Parent | on HN ]