Unverified50% confidenceBenchmarkExact time
动态GGUF的UD-IQ2_XXS档位将原始BF16模型体积从54.7GB压缩到约9GB，体积压缩率83.5%，准确率保留82.5%
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/24/2026
First Seen
Valid until: 11/22/2026
Sources
Related Entities
Related Claims
UnverifiedFP8量化可将7B模型权重从约14GB（FP16）压缩至约7GB76% similarUnverified原版QW3.6 27B模型文件体积约为54GB，Prismo通过数学压缩技术压缩至不到4GB，压缩比超过13倍，且声称不影响模型性能76% similarUnverifiedGGUF 量化格式可将FP16或BF16精度模型压缩至4-bit乃至2-bit精度75% similarUnverified70B模型在INT4精度下可压缩至约35GB75% similarUnverified一个1T参数模型以BF16精度存储需要约2TB显存，INT4量化压缩也需500GB以上75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/795628API
curl https://kongchang.com/api/v1/knowledge/claims/795628MCP
get_claim(id=795628)