Together AI 已宣布 NVIDIA 的 Nemotron 3.5 Lightning 模型现已可用。该开放模型专为大批量、专业化的代理工作负载而设计，可提供高达 4 倍的吞吐量和 30% 的任务完成速度。它采用 30B 混合 MoE 架构，拥有 3B 活跃参数、1M 上下文窗口和 DFlash 推理解码，使其成为开发人员快速且可定制的选择。 AI
影响 为大批量代理任务提供了一个快速、开源的模型，有可能加速专业化人工智能应用的开发。
排序理由 前沿实验室模型发布，附带系统卡。
在 X — Together (inference / OSS) 阅读 →
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
As AI shifts from chatbots to autonomous agents, open models are serving market demands for full control over where AI runs and how it’s deployed and evolves. Today, NVIDIA is expanding its Nemotron 3 model family with Nemotron 3.5 Lightning, the highest-efficiency model in its c…
Nemotron 3.5 Lightning is available on Together AI through Dedicated Model Inference, giving teams reserved capacity and predictable performance for high-volume agent workloads. Start building: https://t.co/4U09N6nL56
What Nemotron 3.5 Lightning brings: → Fastest open model in its class → Up to 4x higher throughput → Up to 30% faster task completion → 30B hybrid MoE (3B active) → 1M context and DFlash speculative decoding → Open and customizable for post-training
NVIDIA Nemotron 3.5 Lightning is now live on Together AI. The fastest open model in its class is built for always-on agents that need to complete high-volume, specialized work quickly. https://t.co/ScHmJGOIGk