NVIDIA Nemotron 3.5 Super VL 上架 Ollama,可本地运行
NVIDIA 的多模态推理模型 Nemotron 3.5 Super VL 能在 Ollama 上一条命令本地跑,单卡智能体吞吐号称高 5 倍,动手党可以试试。
NVIDIA 的 Nemotron 3.5 Super VL 现已登陆 Ollama,通过 ollama run nemotron-3.5-super 即可拉起。该模型结合推理能力与视觉理解,面向多种智能体工作流。官方称在单张 GPU 上,其智能体任务吞吐量比同尺寸级开源模型最高高 5 倍。
NVIDIA Nemotron 3.5 Super VL is now available on Ollama This model combines reasoning and visual understanding across a range of agent workflows. On a single GPU, this model delivers up to 5x higher throughput for agentic tasks compared to other open models in its size category. ollama run nemotron-3.5-super 💬 3 🔄 2 ❤️ 12 👀 1473 📊 4 ⚡