Hey guys,

What’s currently the best LLM for low-VRAM machines with only 6 GB VRAM? I’ve got 32GB RAM as well.

I’m experimenting a little with SillyTavern and I’m curious which model gets the most out of my setup. Should be multilingual and suitable for “casual chatting”.

I know I will probably not get very far with this, but I’m still interested in how far we’ve already come.

(Using KoboldCPP if that matters).

~sp3ctre

  • sp3ctre@feddit.orgOPEnglish
    5·
    3 days ago

    Doesn’t necessarily need to be very fast, but I don’t plan to wait a minute for one simple sentence as well :)

    Is that possible without tinkering too much?

    • Multiplexer@discuss.tchncs.deEnglish
      6·
      3 days ago

      I have a Qwen3.6-35b-a3b model running on a dated desktop machine with 4GB VRAM.
      I use 8-bit-quant, but also have 48GB normal RAM.
      Delivers ~7tk/s, which is already totally usable for most things.
      Tried it on my recent Core-i7 company laptop with 8GB VRAM and got 20tk/s.
      Oh, and I am also using KoboldCPP (on a Linux foundation).

    • Rhaedas@fedia.io
      3·
      3 days ago

      There’s been a few videos on Youtube lately discussing using a particular Qwen model that lets you load only particular expert sections at a time onto the GPU and the rest in RAM. This one was the first I watched (https://www.youtube.com/watch?v=8F_5pdcD3HY), I haven’t tried it, but it makes sense on why it would work.

    • lime!@feddit.nuEnglish
      1·
      3 days ago

      with a 20b model on weak hardware you’ll be waiting more like 10 minutes. unless the os clobbers your process for using too much memory.