NVIDIA 发布 Nemotron 3.5 Super VL，接入 LangChain Deep Agents
Nemotron 3.5 Super VL from @NVIDIAAI brings vision, reasoning & tool use to Deep Agents via ChatNVID...
NVIDIA 开源了这个 120B 参数的视觉智能体模型，跑 LangChain 测试比 DeepSeek V4.1 Flash 快一半，做智能体的可以试试。
NVIDIA 推出 Nemotron 3.5 Super VL，具备视觉理解、推理和工具调用能力，可通过 ChatNVIDIA 接入 LangChain 的 Deep Agents，模型权重开放。该模型总参数量 120B，激活参数 12B，在 LangChain 的 Deep Agents 行为测试套件中平均通过率 87%。速度方面，在 Harbor-lite 基准上总任务耗时比 DeepSeek V4.1 Flash 少 55%，成功率相近。
Nemotron 3.5 Super VL from @NVIDIAAI brings vision, reasoning & tool use to Deep Agents via ChatNVID...
Nemotron 3.5 Super VL from @NVIDIAAI brings vision, reasoning & tool use to Deep Agents via ChatNVIDIA. Open weights. 120B parameters, 12B active. Nemotron 3.5 Super VL averaged an 87% pass rate on our Deep Agents behavioral suite. Speed stood out, too. On our Harbor-lite benchmark: 55% less total task time than DeepSeek V4.1 Flash, with similar success. docs.langchain.com/oss/python/int… 💬 6 🔄 0 ❤️ 18 👀 1964 📊 7 ⚡
