NVIDIA推出Nemotron 3 Nano Omni模型，多模态推理效率提升9倍
Odaily星球日报讯 NVIDIA 在 X 平台发文表示，今日推出开源多模态模型 Nemotron 3 Nano Omni。该模型采用 30B-A3B 混合专家架构（MoE），支持 256K 上下文，可统一处理视频、音频、图像及文本输入。与同类交互水平的开源全能模型相比，该模型吞吐量提升达 9 倍，大幅降低推理成本并提高扩展性。目前 Nemotron 3 Nano Omni 已在 Hugging Face、OpenRouter 及 NVIDIA NIM 上线，并获得 Aible、Applied Scientific Intelligence、H Company 等企业采用。
Disclaimer: OKX Orbit content is provided for informational purposes only. Learn more
Replies
Related Flash News
Odaily•5h agoThe U.S. semiconductor sector staged a "V-shaped" reversal during the session, and the decline of many stocks narrowed sharply or even turned up
ChainCatcher•10h agoU.S. stock index futures edged lower, and semiconductor stocks continued to fall
币界网•10h agoBitget Wallet adds 130 new Xstocks tokenized stocks
币界网•11h agoZyphra releases the first MI355X inference review: long text is close to B200
ChainCatcher•12h agoInstitutions: AI data center demand may drive the revaluation of Bitcoin miners, and more than $90 billion in cooperation has been announced
币界网•12h agoDell has teamed up with Palantir to launch a native AI operating system: the underlying storage replaces Ceph, directly targeting defense and core banks
币界网•17h agoAnalog Devices plans to acquire Empower for $1.5 billion, challenging Nvidia's supplier MPS
TechFlow•23h agoWEEX Labs: AI and the financial sector resonate stronger, and U.S. stock risk appetite continues to pick up
ChainCatcher•1d agoThe three major stock indexes closed mixed, with Li Auto falling nearly 10%
ChainCatcher•1d agoThe three major U.S. stock indexes turned down, with Micron Technology falling nearly 3%