More Quants pls~
#1
by Neiyra - opened
Thanks for making this :)
Would it be possible to also provide Q6 and Q8? It would be the sweet spot between quality and size.
+1 to thanks for this work! My ask is for NVFP4 version if that is possible. I would be very thankful!
@Arya123456 I added the BF16 GGUF so it can be custom quantized as needed, the Q6/Q8 quants are now available here: https://huggingface.co/Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM
@spider1989 - Done. you can find the NVFP4 quant here: Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM-NVFP4
Thanks. But that one is for sm121. I need for sm120