Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning Paper • 2604.12374 • Published Apr 14 • 37
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 Text Generation • 67B • Updated 20 days ago • 970k • 310
view post Post 11088 1440GB of VRAM is incredibly satisfying 😁 See translation 17 replies · 🔥 32 32 👀 10 10 ❤️ 4 4 🤯 2 2 + Reply