Are there models better than these ones right now that I can use? I want ERP coomer models. The nemo one is my go-to when I want fast tokens since it fits in vram, but the quality is shittier when compared to QwQ snowdrop.
Running nvshitia 3070 8gb vram & 64gb ram, with amd 3600 cpu.
trashpanda-org_QwQ-32B-Snowdrop-v0-IQ4_XS
NemoReRemix-12B-Q3_K_XL