Comment by nozzlegear
19 hours ago
I've heard 27B is smarter! I tried it some time ago but couldn't get it working with my oMLX. I need to try it again.
19 hours ago
I've heard 27B is smarter! I tried it some time ago but couldn't get it working with my oMLX. I need to try it again.
Honestly the 27b dense one punches way above its weight in a lot of domains, especially coding in my testing, so I think you will probably be disappointed.
In my case I would say they are comparable but moe models are looping and getting lost a lot more than dense models.
On the other hand having 90t/s with any local model is nice and Pi with loop police extension can prevent looping a lot.
Looping seems related to quantization and not the model itself. If youre digging deep into quants to get working context then yeah.