Quantization
#9
by PacmanIncarnate - opened
Would you look at creating a GGUF version?
It would be wonderful to see a quantized version of this for use with lower VRAM quantities locally.
Quantised versions exist - just search orpheus in models on HF and you'll find a bunch - the most popular one afaik is
Closing this for now - feel free to reopen!
amuvarma changed discussion status to closed