If you've got a decent Nvidia GPU and are hoping on linux, look into the Kobold-cpp Vulkan backend, in my experience it works far better than the CUDA backend and is astronomically faster than the CPU-Only backend.

[–] mstrk@lemmy.world 2 points 1 day ago (1 children)

Will look into that when I have some money to invest. Thank you 💪

[–] ArsonButCute@lemmy.dbzer0.com 1 points 1 day ago

When/If you do, a RTX3070-lhr (about $300 new) is just about the BARE MINIMUM for gpu inferencing. Its what I use, it gets the job done, but I often find context limits too small to be usable with larger models.

If you wanna go team red, Vulkan should still work for inferencing and you have access to options with significantly more VRAM, allowing you to more effectively use larger models. I'm not sure about speed though, I haven't personally used AMDs GPUs since around 2015.