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
[–] 1 point 6 days ago*

If they can make the KV cache size scale more efficiently with many tokens, like DeepSeek 4.1 Flash fitting 1 million tokens in 890MB, it might give them enough room to add a couple billion parameters of weights and still fit well in 32GB GPUs

  • source
  • parent