Unverified50% confidenceFactExact time
The A100 (2020) delivers 312 TFLOPS of FP16 compute and 2 TB/s of HBM2e bandwidth; the H100 (2022) increases FP16 compute to 989 TFLOPS and introduces FP8 support for the first time; the B200 (2024) pushes FP8 compute to the 9 PETAFLOPS level with HBM3e bandwidth reaching 8 TB/s.
1
Sources
50%
Confidence
Long-term
Relevance
9/10/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedNVIDIA's H100 is based on the Hopper architecture, uses HBM3 memory with a bandwidth of up to 3.35 TB/s, and delivers single-card FP16 compute of nearly 2,000 TFLOPS.76% similarVerifiedRTX 4090的理论FP16算力为82.6 TFLOPS，显存带宽为1008 GB/s72% similarVerifiedThe H100 SXM5's HBM3 bandwidth is approximately 3.35 TB/s, and its FP16 peak compute is approximately 989 TFLOPS.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/891630API
curl https://kongchang.com/api/v1/knowledge/claims/891630MCP
get_claim(id=891630)