Unverified50% confidenceBenchmarkExact time
UD-IQ1_S量化版本体积83GB，Top-1精度为73%，是压缩最激进的版本
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/7/2026
First Seen
Valid until: 11/5/2026
Sources
Related Claims
UnverifiedUD-Q4_K_XL量化版本体积155GB，Top-1精度为96%79% similarUnverifiedIQ4_XS量化文件大小15.57GB，pp2048为95.4 tok/s，tg128为10.9 tok/s69% similarVerifiedThe IEEE 754 double-precision format uses 64 bits of storage: 1 sign bit, 11 exponent bits, and 52 mantissa bits (53 bits of effective precision including the implicit leading 1 bit).65% similarUnverifiedA 70B model can be compressed to approximately 35GB at INT4 precision.64% similarUnverifiedGB200 NVL72在FP8精度下的AI算力可达1.44 ExaFLOPS63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/705391API
curl https://kongchang.com/api/v1/knowledge/claims/705391MCP
get_claim(id=705391)