Unsloth 发布 M3.1 Flash 量化版：IQ1_M 保留 89.9% top-1

Daniel Han @danielhanchen原推发布于 2026.10.26

在 X 上打开原推

We made Unsloth UD3 MiniMax-M3.1-Flash quants! We tested across multiple domains to ensure our quants work great for them as well! By default, MiniMax-M3.1-Flash uses NVFP4 for MoE layers and BF16 / MXFP8 for the rest. UD-IQ1_M retains ~89.9% top-1%. Works in Unsloth Desktop!

这条是引用着另一条写的：「Unsloth 发布 M3.1 Flash 2-bit GGUF：150GB 内存可跑」