Oh, that part is. But the splitting tech is built into llama.cpp

With modern methods sometimes running a larger model split between GPU/CPU can be fast enough. Here’s an example https://dev.to/maximsaplin/llamacpp-cpu-vs-gpu-shared-vram-and-inference-speed-3jpl

fp8 would probably be fine, though the method used to make the quant would greatly influence that.

I don’t know exactly how Ollama works but a more ideal model I would think would be one of these quants

https://huggingface.co/bartowski/Qwen2.5-Coder-1.5B-Instruct-GGUF

A GGUF model would also allow some overflow into system ram if ollama has that capability like some other inference backends.

The technology for quantisation has improved a lot this past year making very small quants viable for some uses. I think the general consensus is that an 8bit quant will be nearly identical to a full model. Though a 6bit quant can feel so close that you may not even notice any loss of quality.

Going smaller than that is where the real trade off occurs. 2-3 bit quants of much larger models can absolutely surprise you, though they will probably be inconsistent.

So it comes down to the task you’re trying to accomplish. If it’s programming related, 6bit and up for consistency with whatever the largest coding model you can fit. If it’s creative writing or something a much lower quant with a larger model is the way to go in my opinion.

This could be really simple to achieve with polarisation https://en.m.wikipedia.org/wiki/Polarizer

A polarised filter on the headlight with an other one on the windshield. Reflected light would be non polarised, thus not filtered.

Negative. Had to do that to cancel a cell phone plan recently. They sent the text to my other phone while I was on the line with CSR. Though I agree it should have been possible on the website.

Had a DOS game (which was a port of something even older) that started with a “BARBARIAN!”. Had the worst control scheme I’ll ever see. Function keys for fuck’s sake.

“Cryptojacking” has to be the most cyberpunk term to organically arise thus far.

This is just a data harvesting scam. Bring it back to Facebook

No You don’t get to touch those

They haven’t announced any debate schedule yet.

Yeah well. We kind of had to deal with bears the size of a fucking house for a while. At least until we wiped out their main food source. And rival hominids with at least spears.