mixtureofexperts

NVIDIA released Nemotron-3-Ultra-550B-A55B-NVFP4, a 550B parameter model with 55B active parameters, featuring a 1M token context window and configurable reasoning mode. The model uses a hybrid LatentMoE architecture combining Mamba-2, Mixture-of-Experts, and Attention layers with Multi-Token Prediction, trained with NVIDIA's NVFP4 quantization-aware approach.