Model Releases
Nemotron 3 Ultra (550B-A55B) is here - our strongest open-weight model and full training recipe to date. Heavy emphasis on real-world infere…
Nemotron 3 Ultra (550B-A55B) is here - our strongest open-weight model and full training recipe to date. Heavy emphasis on real-world inference efficiency for long-context agentic workloads. Everythin
Nemotron 3 Ultra (550B-A55B) is here - our strongest open-weight model and full training recipe to date. Heavy emphasis on real-world inference efficiency for long-context agentic workloads. Everything is open 🤗: base, post-trained, reward checkpoints, NVFP4 quantized versions, training data, and recipes. Key technical highlights ‼️: - 550B total / 55B active parameters - Hybrid Mamba2-Transformer (~4:1 Mamba:Attention) - Pretrained in NVFP4 on 20T tokens - LatentMoE architecture - Two-stage MOPD post-training - Native MTP Technical details in the thread 👇
Source: Clem Delangue (X) | 2026-06-04