Unverified50% confidenceFactExact time
NVFP4 is a 4-bit floating-point quantization format used to reduce memory usage and improve inference throughput while preserving model accuracy.
1
Sources
50%
Confidence
Long-term
Relevance
9/23/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedNVFP4 is a 4-bit floating-point format (FP4) introduced by NVIDIA, using floating-point representation (including sign bit, exponent bit, and mantissa bit) to cover the numerical space in a non-uniform manner.79% similarUnverifiedNVFP4是NF4（Normal Float 4）等学术方案的工程化演进版本77% similarUnverifiedTensorRT-LLM has built-in end-to-end support for quantization formats such as NVFP4, including automatic unpacking of quantized weights, mixed-precision inference scheduling, and operator fusion optimization76% 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75% similarVerifiedNVFP4 is a 4-bit floating-point (FP4) quantization format introduced by NVIDIA, designed specifically for the hardware acceleration capabilities of Blackwell architecture GPUs74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/943351API
curl https://kongchang.com/api/v1/knowledge/claims/943351MCP
get_claim(id=943351)