NVIDIA 新出的 30B MoE 模型，3B 激活参数跑得快，专为智能体场景优化，Fireworks 上直接能用。
NVIDIA 推出 Nemotron 3.5 Lightning，这是一款 30B MoE 模型，仅 3B 参数激活，专为高吞吐智能体任务设计。该模型从 Nemotron 3 Ultra 蒸馏而来，在 PinchBench 和 AA-Omniscience Non-Hallucination 基准上表现强劲。目前已在 Fireworks 平台上线，供开发者用于构建智能体工作流。
Looking for a faster specialized model for your Agent Work? @nvidia Nemotron 3.5 Lightning (30B MoE...
Looking for a faster specialized model for your Agent Work? @nvidia Nemotron 3.5 Lightning (30B MoE, 3B active params) is now live on Fireworks. It’s distilled from NVIDIA Nemotron 3 Ultra to be your high-volume agent engine. With strong performance on PinchBench and top-tier scores in AA-Omniscience Non-Hallucination, Nemotron 3.5 Lightning is engineered for reliable, high-productivity agentic workflows. Built for specialization, not generalization. Start building: app.fireworks.ai/models/firewor… 💬 1 🔄 0 ❤️ 1 👀 355 📊 1 ⚡