- cross-posted to:
- hackernews@lemmy.bestiver.se
- cross-posted to:
- hackernews@lemmy.bestiver.se
Seems like smarter and more efficient quants than normal
You must log in or # to comment.
Is a 35b-a3b planned for 3.8?
They don’t tell us things lol. All they said was
Which sounds like there’s something “better” coming, but doesn’t deny the possibility of 35b-a3b. Which is weird because “better” is subjective and depends on your hardware. It could be smaller and smarter than 3.6 35b, but then people are gonna ask for a 3.8 35b because it should be even smarter.
Yeah I was gonna say, 64b or whatever would be completely useless for me. There’s a reason for that size.
But I guess this at least means they are still looking at that range.
No, but something “medium sized” is scheduled for next week. No idea if they are talking about another 122b or 397b.
There’s no point in this if one runs Q8 right? I guess could save VRAM by dropping down from Q8 to say UD Q6.
they have full range of quants.
But is it worth considering UD Q8_K_L if one is running Q8 K XL ?
They have a graph, differences are tiny at that high end
Your mom’s a more efficient quant.
