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
Polymarket executive: Private key rotation has been completed, and all private keys are planned to be transferred to KMS in the future
The review of the U.S. CLARITY Act may be postponed until July, with the probability of final passage in August affected
Wang Chun, co-founder of F2Pool: Participating in the Mars flyby serves as a reminder to SpaceX not to stray from its vision and not to leave the landing plan to the next generation
Maji Big Brother's Ethereum long positions face partial forced liquidations, current investment return -124.94%
Analysis: $1.26 billion Bitcoin ETF outflow may become a 'reverse buying signal'
About 1,400 electricity theft Bitcoin mining machines were seized in São Paulo state, Brazil
Data: Morgan Stanley increased its holdings by another 14 Bitcoins, bringing total holdings to 3,486
The US FDIC has proposed implementing the Bank Secrecy Act and sanctions compliance requirements for stablecoin issuers
Garrett Jin short over 57,000 ZEC on 3x terms, with a 5x BTC long position showing a floating loss of $920,000
Michael Saylor: Strategy does not rule out selling some Bitcoin in 2026


