Unverified50% confidenceBenchmarkExact time
ExoLabs已能在4台Spark上以每秒30个token的速度运行5500亿参数的Nemotron 3.0
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/19/2026
First Seen
Valid until: 10/17/2026
Sources
Related Claims
Unverified英伟达发布Nemotron 3 Ultra，拥有5500亿参数，采用MoE架构，专面向长时间运行的AI智能体任务68% similarUnverifiedNemotron 系列模型的名称中「Nano」表示参数量在数十亿级别（通常为 4B-8B 参数），适合在单张消费级 GPU 上运行63% similarVerifiedM4芯片的Neural Engine每秒可执行38万亿次运算（38 TOPS）61% similarUnverifiedNVIDIA has developed a model called Nemotron Ultra with 550 billion parameters61% similarUnverified去噪塔仅用2.1万亿token训练，而原始Nemotron Nano使用了25万亿token，因此该模型是解码方式的转换而非更聪明的模型61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/561418API
curl https://kongchang.com/api/v1/knowledge/claims/561418MCP
get_claim(id=561418)