We compressed Hy4-preview from 1.5TB to ~200GiB GGUF and it still works well ! Meet MIX-STQ1_0.The...
Hunyuan(@TXhunyuan)234 字 (约 1 分钟)
85
腾讯团队通过MIX-STQ1_0方法将Hy4-preview模型压缩至200GiB,保持高性能且误差变化小。
入选理由:使用MIX-STQ1_0量化方法可将1.5TB模型压缩至200GiB
FeaturedTweet#模型压缩#量化#LLM#腾讯#GGUF中英混合
