Unverified50% confidenceFactExact time
NVIDIA芯片从A100（7nm，400W TDP）到H100（4nm，700W TDP，推理吞吐提升约6倍）再到B200（4nm，1000W TDP，性能再提升约4倍）
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/18/2026
First Seen
Valid until: 11/16/2026
Sources
Related Claims
UnverifiedNVIDIA H100单卡热设计功耗（TDP）约700W，一个万卡集群的理论峰值功耗超过7兆瓦79% similarVerifiedNVIDIA H100单卡FP64双精度浮点性能达到约34 TFLOPS74% similarUnverified看芯片而非标称速率：搭载骁龙X62/X65基带的下行可达4-10Gbps，而入门级骁龙X55/X12方案实际下行约1-2Gbps，标称峰值速率在弱信号下参考意义有限73% similarUnverified1080P高刷电竞主打（240Hz以上）时CPU是瓶颈，应优先i5-14600KF/R5 7600X级别以上；4K游戏则CPU压力小，预算应倾斜给显卡73% similarUnverifiedNVIDIA A100、H100系列GPU单卡功耗可达300-700瓦72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/771171API
curl https://kongchang.com/api/v1/knowledge/claims/771171MCP
get_claim(id=771171)