Event ·Multi-source

NVIDIA 发布开源模型 Nemotron 3.5 Super VL，主打视觉理解与工具调用

NVIDIA 在 Nemotron 开源模型家族中新增 Nemotron 3.5 Super VL。该模型把视觉理解、推理和工具调用整合在一个模型里，面向需要完成多步任务的 AI Agent。作为开放权重模型，开发者可以自行定制和部署，不依赖闭源 API。

Current read

NVIDIA 又添了一个开源多模态模型，视觉加工具调用一体化，想自己部署 Agent 的话可以看看它和 Qwen-VL 比怎么样。

11 sources62° AI heatLast updated 2026/10/15 15:10:27

Evidence

11 sources

Primary sourceNVIDIA

2026/10/15 15:10:27View source

Related source 1Together AI

2026/10/15 15:01:33View source

Related source 2OpenRouter

2026/10/15 15:30:15View source

Related source 3vLLM

2026/10/15 15:50:21View source

Related source 4Decoder

2026/10/15 16:09:44View source

Related source 5TestingCatalog

2026/10/16 07:05:02View source

Related source 6CoreWeave

2026/10/15 16:28:42View source

Related source 7Nous Research

2026/10/15 17:32:59View source

Related source 8Aravind Srinivas

2026/10/15 18:59:46View source

Related source 9marktechpost

2026/10/15 19:53:50View source

Related source 10ollama

2026/10/15 23:50:31View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story