Model Releases
NVIDIA Nemotron 3 Ultra Powers Faster, More Efficient Reasoning for Long-Running Agents
NVIDIA's Nemotron 3 Ultra is a 550B-parameter Mixture-of-Experts model with 55B active parameters, optimized for orchestrating complex, long-running agent workflows by combining frontier reasoning and
NVIDIA's Nemotron 3 Ultra is a 550B-parameter Mixture-of-Experts model with 55B active parameters, optimized for orchestrating complex, long-running agent workflows by combining frontier reasoning and high throughput with domain adaptability. The model features hybrid Mamba-Transformer layers for efficient long-context handling, NVFP4 quantization for up to 5x higher throughput, and multi-token prediction for improved generative speed. Nemotron 3 Ultra lowers the cost for agentic tasks by up to 30%.
Source: NVIDIA Developer | 2026-06-04