Unverified50% confidenceFactExact time
NVIDIA natively supported the FP8 data type starting from the Hopper architecture, and the Blackwell architecture further added support for FP4.
1
Sources
50%
Confidence
Long-term
Relevance
8/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedHopper架构的H100支持FP8，这是与Blackwell原生FP4支持的重要区别78% similarVerifiedNVIDIA Blackwell 架构于2024年发布，是继 Hopper（H100）之后的新一代数据中心 GPU 架构77% similarPartially VerifiedNVFP4 is a 4-bit floating-point (FP4) quantization format introduced by NVIDIA, designed specifically for the hardware acceleration capabilities of Blackwell architecture GPUs75% similarUnverifiedNVIDIA在Hugging Face发布Qwen3 235B的NVFP4量化模型，NVFP4是针对Hopper和Blackwell架构的4-bit浮点格式，理论压缩比达4倍73% similarUnverifiedFP8 is a low-precision computing format natively supported by the Blackwell architecture, including two variants—E4M3 and E5M2—and the Tensor Core's FP8 compute throughput is twice that of FP16.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/828101API
curl https://kongchang.com/api/v1/knowledge/claims/828101MCP
get_claim(id=828101)