MiniMax highlights local quantization work for M3.1 Flash
MiniMax highlighted community efforts to run its 428B-parameter MiniMax M3.1 Flash model locally using lower-bit weights, specialized kernels, and expert placement across GPUs and system RAM. The projects include Unsloth's 143.9 GB 2-bit Dynamic GGUF weights, ViC305's SAGE-EXL3 recipe for one DGX Spark, PeasantSmith's Project Maya quantizations, and additional work from MiaAI Lab, oMLX, and others. A LocalLLaMA review noted that the reported sizes, fidelity scores, and speed figures used separate evaluation sets and are not directly comparable.
MiniMax says the community work expands the hardware options for deploying its 428B model locally, while the documented weights, hardware recipes, and fidelity measurements give developers concrete starting points.
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