Mamba-Moe

1 prompts in this category

llm nemotron-3 nvidia Nemotron-3-Ultra

Optimized prompts for NVIDIA Nemotron 3 Ultra — the first open-weight 550B hybrid Mamba-MoE model. 55B active parameters, 1M context window, 89.1 MMLU. Datacenter-scale agentic reasoning.

View