Comment by traceroute66
15 hours ago
> 35B MoE is certainly a good and fast local model. I find 27B dense to be quite a bit smarter
Isn't that just the definition of MoE vs dense ?
15 hours ago
> 35B MoE is certainly a good and fast local model. I find 27B dense to be quite a bit smarter
Isn't that just the definition of MoE vs dense ?
Full name is 35B-A3B. 3B Is the token generator thats selected out of the 35b available in the model, which is some layered jazz.
So it can be dumber but its quite capablr.