Unverified50% confidenceFactExact time
Single-precision floating-point numbers store the exponent in 8 bits using biased encoding with bias = 127.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedINT8 quantization maps 32-bit floating-point weights to 8-bit integers, compressing model size by 75% with almost no accuracy loss71% similarUnverifiedFor the 7B model, accuracy with the solver was 75.31% versus 72.02% for direct calculation, a paired improvement of +3.29 percentage points, with a 95% cluster interval of [-3.49, 10.38] crossing zero, making the advantage non-significant.69% similarUnverifiedQ8_0 quantization compresses model weights from 32-bit floating-point numbers to 8-bit integers, with precision loss typically within 1% compared to FP32.66% similarUnverifiedAdding 7 and then taking modulo 7 is equivalent to doing nothing, and can be used to shift negative remainders into the positive range.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1002450API
curl https://kongchang.com/api/v1/knowledge/claims/1002450MCP
get_claim(id=1002450)