MiniMax_AI· @MiniMax_AI · X·· 1 天前AI 评分
MiniMax M3.1 Flash 通过 Unsloth 提供 2-bit 量化与本地部署路径
MiniMax M3.1 Flash 经 Unsloth Dynamic GGUFs 转换为 143.9GB 的 2-bit 版本，在其七个领域评测中达到 91.5% 的 top-1 token 一致率。
MiniMax M3.1 Flash meets the @UnslothAI community. 🐙🦥✨
Unsloth’s Dynamic GGUFs bring our 428B MoE model to a 143.9GB 2-bit footprint, with 91.5% top-1 token agreement in their evaluation across seven domains.
That means a lower memory barrier to self-hosting, deployment through Unsloth Desktop and llama.cpp, and an OpenAI-compatible API for existing apps and agents.
With 78K+ GitHub stars and over 500M model downloads on Hugging Face, Unsloth gives M3.1 Flash a path into an established community of developers running, evaluating and building with open models.
Open weights. Local control. More ways to build.
来源：MiniMax_AI · x.com