Is a 35b-a3b planned for 3.8?
this post was submitted on 19 Aug 2026
52 points (94.8% liked)
LocalLLaMA
5071 readers
18 users here now
Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.
Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.
As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.
Rules:
Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.
Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.
Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since <over 10 years ago>.
Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.
founded 3 years ago
MODERATORS
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.
Your mom's a more efficient quant.