Archive link: https://archive.ph/U1zEK

you are viewing a single comment's thread
view the rest of the comments
[–] 2 points 2 weeks ago

24 is ideal, 16 works fine especially with some MoE offloading. If you use llama-swap, a fast PCIe bus and fast storage is ideal. Takes about 20 seconds to swap between two models on my X570 board.

  • source
  • parent