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
[–] 2 points 5 days ago (1 child)

They've changed the license with Qwen 4, starting with 3.8-next. So I probably won't be using any further releases

  • source
  • hideshow 1 child comment