Verified65% confidenceFactExact time
The MXFP4 format has a group of elements (typically 32) sharing a single 8-bit scaling factor, with each element represented by a 4-bit micro floating-point number (1 sign bit + 2 exponent bits + 1 mantissa bit).
3
Sources
65%
Confidence
Long-term
Relevance
8/7/2026
First Seen
Sources
Q8_K_XL与MXFP4命名之争：FP8≠Q8_0的量化真相
Related Claims
VerifiedMXFP4 mitigates numerical overflow and precision degradation at 4-bit low precision by sharing a single scaling factor within small blocks of data (typically 32 elements), theoretically reducing memory footprint and bandwidth requirements by approximately 4× compared to FP16.79% similarUnverifiedTaking the Q4_0 format as an example, every 32 FP32 weights are packed into one quantization block containing one scale factor and 32 4-bit integers, averaging approximately 4.5 bits per parameter, reducing memory usage to approximately 1/8 of the original.69% similarUnverifiedFP32 uses 32 bits to represent floating-point numbers, consisting of 1 sign bit, 8 exponent bits, and 23 mantissa bits.64% similarUnverifiedIn FP16 format each parameter occupies 2 bytes, while in INT4 format it occupies only 0.5 bytes, theoretically achieving a 4x compression ratio.63% similarUnverifiedFP16使用16位存储数值（1位符号位、5位指数位、10位尾数位），可表示约65000个离散值62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/699424API
curl https://kongchang.com/api/v1/knowledge/claims/699424MCP
get_claim(id=699424)