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.
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.