LLM EXPLORER 65,695 MODELS INDEXED

MiniMax M3.1 Flash Text 4bit by mlx-community

By mlx-community · 475 downloads
HF Repo ↗ Copy URL

MiniMax M3.1 Flash Text 4bit is an open-source language model by mlx-community. Features: 426.2b LLM, VRAM: 177.2GB, License: other, Quantized, LLM Explorer Score: 0.34.

  4bit   8-bit   Agent Base model:minimaxai/minimax-m... Base model:quantized:minimaxai...   Coding   Conversational   Custom code   Minimax m3 vl   Mlx   Moe   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/MiniMax-M3.1-Flash-Text-4bit 

MiniMax M3.1 Flash Text 4bit Parameters and Internals

LLM NameMiniMax M3.1 Flash Text 4bit
Repository 🤗https://huggingface.co/mlx-community/MiniMax-M3.1-Flash-Text-4bit 
Base Model(s)  MiniMaxAI/MiniMax-M3.1-Flash   MiniMaxAI/MiniMax-M3.1-Flash
Model Size426.2b
Required VRAM177.2 GB
Updated2026-10-26
Maintainermlx-community
Model Typeminimax_m3_vl
Model Files  5.0 GB: 1-of-58   4.2 GB: 2-of-58   4.2 GB: 3-of-58   4.2 GB: 4-of-58   4.2 GB: 5-of-58   4.2 GB: 6-of-58   4.2 GB: 7-of-58   4.2 GB: 8-of-58   4.2 GB: 9-of-58   4.2 GB: 10-of-58   4.2 GB: 11-of-58   4.2 GB: 12-of-58   4.2 GB: 13-of-58   4.2 GB: 14-of-58   4.2 GB: 15-of-58   4.2 GB: 16-of-58   4.2 GB: 17-of-58   4.2 GB: 18-of-58   4.2 GB: 19-of-58   4.2 GB: 20-of-58   4.2 GB: 21-of-58   4.2 GB: 22-of-58   4.2 GB: 23-of-58   4.2 GB: 24-of-58   4.2 GB: 25-of-58   4.2 GB: 26-of-58   4.2 GB: 27-of-58   4.2 GB: 28-of-58   4.2 GB: 29-of-58   4.2 GB: 30-of-58   4.2 GB: 31-of-58   4.2 GB: 32-of-58   4.2 GB: 33-of-58   4.2 GB: 34-of-58   4.2 GB: 35-of-58   4.2 GB: 36-of-58   4.2 GB: 37-of-58   4.2 GB: 38-of-58   4.2 GB: 39-of-58   4.2 GB: 40-of-58   4.2 GB: 41-of-58   4.2 GB: 42-of-58
Quantization Type4bit
Model ArchitectureMiniMaxM3SparseForConditionalGeneration
Licenseother
Transformers Version4.52.4
Torch Data Typebfloat16