Unverified50% confidenceBenchmarkExact time

使用NVIDIA B300芯片在1兆瓦数据中心可实现约45万token/s总吞吐量，若每用户340 token/s则约1324个并发活跃用户

1

Sources

50%

Confidence

Medium-term (~90 days)

Relevance

7/21/2026

First Seen

Valid until: 10/19/2026

Sources

GPT-5.6 Inference at 18x Speed: OpenAI's Compute Gamble and Business Logic

Related Claims

UnverifiedThe NVIDIA A100 has a memory bandwidth of 2 TB/s; loading a 280 GB FP32 model takes approximately 140 ms, meaning weight loading alone limits generation to a maximum of approximately 7 tokens per second.72% similar UnverifiedThe HBM memory bandwidth of the NVIDIA H100 is approximately 3.35 TB/s, and its utilization rate in autoregressive generation tasks is often below 10%.70% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/580876

API

curl https://kongchang.com/api/v1/knowledge/claims/580876

MCP

get_claim(id=580876)