MiniMax M3.1 Flash 量化版开源落地，428B 模型可本地部署
428B 的 MiniMax M3.1 Flash 被社区量化到 143.9 GB，从 RTX 3090 到 Mac 都有现成方案，想本地跑的看过来
MiniMax M3.1 Flash 是一个 428B 参数模型，官方汇总了社区对其的多种量化方案。UnslothAI 提供 2-bit Dynamic GGUF 权重，体积压到 143.9 GB。SAGE-EXL3、Project Maya、oQ 等方案分别覆盖 DGX Spark、Apple Silicon 和 4× RTX 3090 等硬件，AMD Instinct 也有 Quark MXFP4 适配。量化通过降低权重位宽减少显存占用和解码时的数据搬运。
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.
