Expired50% confidenceFactTime unknown
The NVIDIA Blackwell architecture (B200/GB200) supports FP4 computation, theoretically doubling Tensor Core throughput once again.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Related Claims
UnverifiedThe NVIDIA Blackwell architecture (GB200/B200 series) introduces native FP4 tensor cores at the hardware level81% similarUnverifiedNVIDIA designed a dedicated Tensor Core instruction mma.kind::mxf4 for NVFP4 in the Blackwell architecture (SM 100/103, such as the B100 and B200 series), and adopted an FP8 scaling factor mechanism with one scale per group of 16 elements.81% similarVerifiedOn NVIDIA GPUs equipped with Tensor Cores (such as A100 and H100), the throughput of FP16/BF16 matrix operations can reach 2–8 times that of FP32.80% similarUnverifiedNVIDIA's Blackwell architecture (B100/B200) natively supports matrix operations in MXFP4 format at the hardware level, with throughput nearly doubling compared to FP8.79% similarUnverifiedConverting from FP32 to FP16 can achieve a 2–4x throughput improvement on the Tensor Cores of modern GPUs.79% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/61136API
curl https://kongchang.com/api/v1/knowledge/claims/61136MCP
get_claim(id=61136)