Unverified50% confidenceReleaseExact time
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
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/21/2026
First Seen
Valid until: 10/19/2026
Sources
Related Claims
UnverifiedQ3_K_M将每个权重压缩至约3bit，27B模型权重体积可降至约12～13GB82% similarUnverifiedBonsai将27B模型从全精度的54GB压缩至3.9GB80% similarUnverifiedPrismo宣称其方案让270亿参数全部同时激活，并将原版54GB的QW3.6模型压缩至不到4GB，压缩比超过13倍且声称不影响性能78% similarVerifiedQwen2.5:7B模型Q4量化后文件大小约为4GB77% similarUnverifiedPrismML将Qwen 3.6从原始约54GB压缩到不足4GB，压缩比超过13倍77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/584668API
curl https://kongchang.com/api/v1/knowledge/claims/584668MCP
get_claim(id=584668)