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
币界网•20h agoInstitutions: The S&P 500 index is poised for its strongest earnings growth since 2021
Blockbeats•21h agoAnalysis: SpaceX's IPO may expand Nasdaq BTC exposure, but may be a short-term bearish factor for tech stocks and the siphoning of Bitcoin funds
ChainCatcher•1d agoAI startup Hark completed a $700 million Series A round at a $6 billion valuation, led by Parkway Venture Capital
Odaily•1d agoThe White House postponed the signing ceremony of the AI executive order
Odaily•1d agoNvidia's stock price fell by 2%, and Intel's decline widened to 4.3%.
ChainCatcher•1d agoU.S. stocks may give back gains as crude oil prices and Treasury yields rebound
币界网•1d agoSuper-rich family offices increased their holdings in chip stocks in the first quarter
Blockbeats•1d agoAfter Nvidia's earnings report, several investment banks raised their target prices
币界网•2d agoThe market is concerned that Nvidia's future will continue to exceed expectations, which still needs to be verified
Odaily•2d agoMost crypto sectors rose before the US stock market opened, with Circle (CRCL) up over 1%