• 0 Posts
  • 46 Comments
Joined 1 year ago
cake
Cake day: June 12th, 2023

help-circle

  • Taking ollama for instance, either the whole model runs in vram and compute is done on the gpu, or it runs in system ram and compute is done on the cpu. Running models on CPU is horribly slow. You won’t want to do it for large models

    LM studio and others allow you to run part of the model on GPU and part on CPU, splitting memory requirements but still pretty slow.

    Even the smaller 7B parameter models run pretty slow in CPU and the huge models are orders of magnitude slower

    So technically more system ram will let you run some larger models but you will quickly figure out you just don’t want to do it.











  • Synology nas are nice. I will say there’s definitely a nice UI there and they generally work well. But there is a good bit of lock-in and there are some really reasonable roll-your-own hardware and software options these days.

    If you want something that just works, doesn’t need to be super configurable and is easiest to set up and manage, get a synology. If you don’t mind putting in some work or if you need to really tweak some stuff, roll your own