Unverified60% confidenceFactExact time
The H100's fourth-generation Tensor Core natively supports FP8, with a peak compute of 3958 TFLOPS, which is twice that of FP16.
2
Sources
60%
Confidence
Long-term
Relevance
7/22/2026
First Seen
Sources
Related Claims
UnverifiedV100的Tensor Core在FP16精度下峰值算力可达125 TFLOPS，是前代Pascal架构的5倍以上80% similarUnverifiedH100的Transformer Engine支持FP8精度，张量核心在FP8模式下峰值算力可达3958 TFLOPS，FP16为1979 TFLOPS79% similarUnverifiedAs a data center flagship, the P100 is equipped with dedicated FP16 SIMD units, theoretically capable of 21.2 TFLOPS of FP16 compute, making it the only model in the Pascal family with fast fp16 hardware units.79% similarVerifiedThe H100 GPU adopts NVIDIA's Hopper architecture, with a single-card peak compute of 3,958 TFLOPS (FP16 precision).76% similarUnverifiedNative FP8 hardware acceleration was first implemented in the fourth-generation Tensor Cores of the NVIDIA Hopper architecture (H100, 2022), with a peak throughput of 3958 TFLOPS.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/593790API
curl https://kongchang.com/api/v1/knowledge/claims/593790MCP
get_claim(id=593790)