Basically the title.

For me, a dense model around 20b, with an additional engram table of 10-20b, or a sparse MoE around 80b would be amazing.

you are viewing a single comment's thread
view the rest of the comments
[–] 5 points 6 days ago

32GB RAM and 8GB VRAM here, so 35b a3b is about my maximum, maybe with added n-grams

  • source