精选理由
NVIDIA开源了30B MoE，激活才3B，跑起来便宜，还配了个路由器帮你省钱，搞智能体的可以看看。
NVIDIA推出开源MoE模型Nemotron 3.5 Lightning，总参数量30B，激活参数仅3B，专为智能体执行层设计。同时发布NeMo Switchyard模型路由器，可将每个执行步骤路由到成本最低且能力足够的模型。该组合旨在降低智能体推理成本，提升执行效率。Nemotron 3.5 Lightning基于开源许可发布，开发者可自由使用。
原文 · marktechpost
NVIDIA AI Releases Nemotron 3.5 Lightning: A 30B Open MoE with 3B Active Parameters, and NeMo Switchyard Model Router
NVIDIA's open 30B MoE targets the agent execution layer, with Switchyard routing each step to the cheapest capable model. The post NVIDIA AI Releases Nemotron 3.5 Lightning: A 30B Open MoE with 3B Active Parameters, and NeMo Switchyard Model Router appeared first on MarkTechPost .