gemma-3-4b-it-abliterated.q8q4.gguf is very much appreciated.

#1
by twoxfh - opened

My old igpu laptop appreciates gemma-3-4b-it-abliterated.q8q4.gguf; are you sharing the code of how its made? Curious to see it applied to other models.

Sure:

  1. convert the model to GGUF F16.
  2. quantize the model to q4 but use q8 for the output and embed tensors. (quantize utility has the option for this).

My old igpu laptop appreciates gemma-3-4b-it-abliterated.q8q4.gguf; are you sharing the code of how its made? Curious to see it applied to other models.

check my models, I converted most of them already. https://huggingface.co/ZeroWw

ZeroWw changed discussion status to closed
Your need to confirm your account before you can post a new comment.

Sign up or log in to comment