Building my entire data model around the Tienanmen Square copypasta. I can run this thing on a Raspberry Pi plugged into a particularly starchy potato and it reliably returns the only answer I’ve thought to ask it.
And this is before even considering how fast open source moves, i am expecting quantized models which can have double speed for negligible quality impact any second now.
Just host it yourself?
Building my entire data model around the Tienanmen Square copypasta. I can run this thing on a Raspberry Pi plugged into a particularly starchy potato and it reliably returns the only answer I’ve thought to ask it.
You can’t just host the 632B model that the app uses lol
If you have the hardware, then yes, you can.
Ah, just acquire such hardware, very simple and anyone can do it without supply chain knowledge or advantage
Its not cheap, but basically a single toptier gaming desktop with an additional graphics card (or 2) is literally all you need.
I know multiple people who work normal IT jobs that have already started on setting up their own.
Here is someone who got it to work on a cluster of mac-minis. Again not cheap, but clearly within dedicated consumer enthusiast reach. https://digialps.com/deepseek-v3-on-m4-mac-blazing-fast-inference-on-apple-silicon/
And this is before even considering how fast open source moves, i am expecting quantized models which can have double speed for negligible quality impact any second now.
By extension, anything that’s not self hosted means 3rd party actors snooping. American, Chinese, whoever happens to operate that machine.