Unverified50% confidenceFactExact time
The H100 is a Hopper-architecture data center GPU released by Nvidia in 2022, built on TSMC's 4N process, equipped with 80GB of HBM3 memory, and capable of delivering about 4000 TFLOPS at FP8 precision.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe H100 GPU adopts NVIDIA's Hopper architecture, with a single-card peak compute of 3,958 TFLOPS (FP16 precision).80% similarUnverifiedThe H100 is based on the Hopper architecture, contains 80 billion transistors, and can deliver approximately 4 petaFLOPS of FP8 compute per card.79% similarUnverified英伟达H100/H200 GPU每颗封装5~6个HBM3e堆栈75% similarUnverifiedH100/H200是英伟达专为大模型训练与推理设计的数据中心级GPU，采用NVLink高速互联技术使数千张卡协同工作73% similarUnverifiedThe NVIDIA H100 is a data center GPU based on the Hopper architecture, with its SXM5 version having a TDP as high as 700W.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1047619API
curl https://kongchang.com/api/v1/knowledge/claims/1047619MCP
get_claim(id=1047619)