Request to add nvfp4 and fp8 quantization for the model.
#9
by makisekurisu-jp - opened
It would be great to add nvfp4 and fp8 quantization for Qwen 3.5 9B and Gemma 4 E4B.
It would be great to add nvfp4 and fp8 quantization for Qwen 3.5 9B and Gemma 4 E4B.