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•12m agoDeposit 3,000 BNB to Pionex 45 minutes before the GMGN fee related address
ChainCatcher•39m agoLegend announced the closure of its operations and will cease operations on July 12
ChainCatcher•49m agoFigures: More than 1 million US merchants now accept Bitcoin payments through Square
ChainCatcher•1h agoCharles Schwab has begun rolling out crypto accounts to retail customers that support direct purchases of Bitcoin and Ethereum
ChainCatcher•1h agoData: The Pendle team deposited 600,000 PENDLE to Binance, worth $1.27 million
Odaily•1h agoBrother Maji held $40.59 million in BTC and ETH long orders, losing $2.16 million in the past week
ChainCatcher•2h agoErik Voorhees linked whales to buy 494 ETH again, bringing the total position to 127,700
Odaily•2h agoBase Leader: x402 now supports batch settlement
ChainCatcher•2h agoAnthropic is in talks to raise at least $30 billion at a $900 billion valuation
Odaily•2h agoSpark launches the 3rd month SPK buyback