Maybe a better alternative to Tiel Coder for people with 32GB RAM and 8GB VRAM

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

How do you run a model split between ram and vram? Everything I've read so far says that will tank performance...

Is it something of a, "it works, but prepare to spend a lot of time at the water cooler" type deal, or am I mis informed?

  • source
  • hideshow 2 child comments
  • [–] 3 points 2 weeks ago

    This one is a Mixture of Experts model (40B total weight, 2.5B active during token generation). Inference engines like llama.cpp have flags you can pass to offload the lesser used experts to system RAM.

    It's slower than having the entire model resident in VRAM, but generally pretty usable.

  • source
  • parent