Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning Paper โข 2604.12374 โข Published 29 days ago โข 36
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 Text Generation โข 67B โข Updated 11 days ago โข 893k โข 300
view post Post 10774 1440GB of VRAM is incredibly satisfying ๐ See translation 17 replies ยท ๐ฅ 32 32 ๐ 10 10 โค๏ธ 4 4 ๐คฏ 2 2 + Reply