MiniMax 展示 M3.1 Flash 本地量化成果
MiniMax 介绍了社区利用低位权重、高效内核以及跨 GPU 与系统内存放置专家来本地运行 428B 参数 MiniMax M3.1 Flash 的进展。其中包括 Unsloth 的 143.9 GB 2-bit Dynamic GGUF 权重、ViC305 面向单台 DGX Spark 的 SAGE-EXL3 配方、PeasantSmith 的 Project Maya 量化方案，以及 MiaAI Lab、oMLX 等团队的工作。LocalLLaMA 用户提醒，各项目公布的体积、保真度和速度数据来自不同评测集，不能直接横向比较。
MiniMax 称这些社区成果扩大了 428B 模型的本地部署硬件选择，而公开的权重、硬件配方与保真度测量为开发者提供了可用的起点。
MiniMax M3.1 Flash, on more of your hardware.
Quantizing a 428B model opens up more ways to run it locally. Lower-bit weights reduce the memory needed to load the model and the weight data moved during decoding. Making those savings useful takes careful calibration, efficient low-bit kernels, and hardware-aware placement of experts across GPU and system RAM.
Thank you to the builders doing that work:
• @UnslothAI @danielhanchen — 2-bit Dynamic GGUF weights at 143.9 GB, with calibration and fidelity testing across coding, tool use and other workloads. • @ViC305 — SAGE-EXL3, token-level fidelity measurements and a single-DGX-Spark recipe. • @PeasantSmith — Project Maya quants and expert offloading for local coding and tool use. • @MiaAI_lab — EXL3-EAQ quantization work. • @jundotkim + mlx-community — oQ quants and DSpark-powered decoding through oMLX on Apple Silicon. • @AIatAMD — Quark MXFP4 adapted for AMD Instinct. • @atomic_chat_hq — GGUFs for local desktop workflows. • @superalesha — custom inference work combining quantized weights, expert caching and system RAM on 4× RTX 3090. Every shared quant, kernel, measurement and recipe gives the next builder a better starting point. Thank you.
#MiniMax#MiniMax M3.1 Flash#Unsloth#SAGE-EXL3#Project Maya#MiaAI Lab#EXL3-EAQ#oMLX#AMD Instinct#DGX Spark