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
ChainCatcher•1h agoData: Tokenized stocks hit a record high in single-day trading volume, reaching $3.57 billion
ChainCatcher•1h agoDeloitte effectively acquired the Blocknative team, which will stop API and Gas Network services
币界网•2h agoThe Trump administration plans to reduce NATO's crisis response forces
币界网•4h agoThe mediators believe that the US-Iran negotiations have made almost no progress, and Iran insists on maintaining its core demands
币界网•5h agoThe total supply of stablecoins exceeded $300 billion, and growth slowed
ChainCatcher•5h agoSenator: The OCC should not grant a national trust license to crypto businesses like Ripple and Coinbase
ChainCatcher•5h agoDeloitte acquires crypto infrastructure company Blocknative
币界网•5h agoWalsh is about to take office and accelerate the completion of financial asset divestiture commitments
ChainCatcher•6h agoCoinbase, Kraken, and Gemini urge the Senate to remove restrictions on crypto token listings
Odaily•7h agoOpenAI联合创始人Andrej Karpathy宣布加入Anthropic