Expired80% confidenceFactTime unknown
NVFP4 relies on the FP4 compute units of Tensor Cores and is currently limited to new cards such as the 5090.
1
Sources
80%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedNVIDIA 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.76% similarUnverified在非50系显卡上使用NVFP4会退化为软件模拟，导致显存占用大、精度差，无任何优势73% similarUnverifiedRTX 5080搭载GB203芯片，提供更高密度的FP8 Tensor Core，并采用GDDR7显存71% similarUnverifiedV100 的 Volta 架构 Tensor Core 仅支持 FP16/FP32 混合精度，不具备原生 FP8 矩阵乘法指令，FP8在V100上无法获得算力加速70% 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 FP32.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/18031API
curl https://kongchang.com/api/v1/knowledge/claims/18031MCP
get_claim(id=18031)