Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> Agents require at least DeepSeek pro and even that is the minimum.

The Granite 4.2 models which are just recently out, are optimized to handle agentic workflows.

For local models, it's about using the right model for the right job.

 help



Waste of time when I can pay $20 a month for sol.

versus $0 with local models.

There will always be a reason to run frontier models, but local models are well at levels that assist with stuff that don't need that level of complexity.


You could buy a $150 refurbished 16gb i5 and use that model until openAI does its IPO and has to become sane again.

But I guess a $2000 Mac is probably better if you don't care about cost or quality.


> You could buy a $150 refurbished 16gb i5

Or I can use the Mac I already have.

Your example though, Ouch!

~8B Q4. That's around 5-10 tokens a second. Base M1 16GB mac would do 15-20 tokens a seconds. That's a 6 year old machine.

You do get what you pay for it seems.


Oh go get a $700 Nvidia laptop.

Sorry local models are basically useless outside chat, I didn't even consider it.


You seem to be ill informed and only talking to yourself at this point.



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: