Request release GGUF Q8_0 Quantized Version
#1
by
makisekurisu-jp
- opened
Hi, thank you very much for your amazing work on this model!
Would it be possible for you to release a GGUF format quantized version with Q8_0 precision? Many of us running on CPU or using tools like llama.cpp or koboldcpp would greatly benefit from a high-precision Q8_0 version for both speed and quality.
Thanks again for your contributions β looking forward to your reply!