NVIDIA新出的开源MoE模型，30B参数但只激活3B，笔记本就能跑，速度还快4倍，做智能体任务很合适。
NVIDIA推出Nemotron 3.5 Lightning，这是一款开放权重的30B MoE模型，仅3B参数激活，专为常驻智能体设计，可高效处理高吞吐、专业化任务。其输出速度比同类模型快4倍，能在笔记本或DGX Spark等本地硬件上流畅运行。用户也可通过Perplexity使用更大的Nemotron Ultra版本。
A great American open weights MoE model that can run efficiently on your laptop or local hardware li...
A great American open weights MoE model that can run efficiently on your laptop or local hardware like the DGX Spark! You can use the larger Nemotron Ultra on Perplexity! NVIDIA AI @NVIDIAAI Introducing NVIDIA Nemotron 3.5 Lightning⚡ An open 30B MoE model with 3B active parameters, built for always-on agents to complete high-volume, specialized tasks faster. It delivers up to 4x the output speed of similar-sized models. 🔗 View Quoted Tweet 💬 3 🔄 3 ❤️ 33 👀 5479 📊 5 ⚡