• CameronDev@programming.dev
    link
    fedilink
    arrow-up
    3
    ·
    edit-2
    8 hours ago

    Full quantisation? I’ve only got a 8GB 3070, but I’ll give it a go

    Edit: Tried the unsloth/qwen3.6 with llama.CPP, and it failed to allocate a 26GB Vulcan buffer and died. Dunno what magic your using, no luck for me though :(

    • stuner@lemmy.world
      link
      fedilink
      arrow-up
      3
      ·
      5 hours ago

      I run it using LM Studio, which defaults to Q4 quantization, I think. I was able to put about 10 layers on the GPU with 64k token context. That put me at about 9.1 GB VRAM usage, leaving some room for Video playback xD