LLM EXPLORER 65,695 MODELS INDEXED

MiniMax M3.1 Flash OQ4e Mtp by mlx-community

By mlx-community · 469 downloads
HF Repo ↗ Copy URL

MiniMax M3.1 Flash OQ4e Mtp is an open-source language model by mlx-community. Features: 427.1b LLM, VRAM: 209.9GB, License: other, LLM Explorer Score: 0.34.

  4-bit Base model:minimaxai/minimax-m... Base model:quantized:minimaxai...   Conversational   Custom code   Image-text-to-text   Minimax m3 vl   Mlx   Mtp   Oq   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/MiniMax-M3.1-Flash-oQ4e-mtp 

MiniMax M3.1 Flash OQ4e Mtp Parameters and Internals

LLM NameMiniMax M3.1 Flash OQ4e Mtp
Repository 🤗https://huggingface.co/mlx-community/MiniMax-M3.1-Flash-oQ4e-mtp 
Base Model(s)  MiniMaxAI/MiniMax-M3.1-Flash   MiniMaxAI/MiniMax-M3.1-Flash
Model Size427.1b
Required VRAM209.9 GB
Updated2026-10-26
Maintainermlx-community
Model Typeminimax_m3_vl
Model Files  5.0 GB: 1-of-46   5.1 GB: 2-of-46   5.4 GB: 3-of-46   5.4 GB: 4-of-46   5.4 GB: 5-of-46   5.4 GB: 6-of-46   5.4 GB: 7-of-46   5.4 GB: 8-of-46   5.4 GB: 9-of-46   5.4 GB: 10-of-46   5.4 GB: 11-of-46   5.4 GB: 12-of-46   5.4 GB: 13-of-46   5.4 GB: 14-of-46   5.4 GB: 15-of-46   5.4 GB: 16-of-46   5.4 GB: 17-of-46   5.4 GB: 18-of-46   5.4 GB: 19-of-46   5.4 GB: 20-of-46   5.4 GB: 21-of-46   5.4 GB: 22-of-46   5.4 GB: 23-of-46   5.4 GB: 24-of-46   5.4 GB: 25-of-46   5.4 GB: 26-of-46   5.4 GB: 27-of-46   5.4 GB: 28-of-46   5.4 GB: 29-of-46   5.4 GB: 30-of-46   5.4 GB: 31-of-46   5.4 GB: 32-of-46   5.4 GB: 33-of-46   5.4 GB: 34-of-46   5.4 GB: 35-of-46   5.4 GB: 36-of-46   5.4 GB: 37-of-46   5.4 GB: 38-of-46   5.4 GB: 39-of-46
Model ArchitectureMiniMaxM3SparseForConditionalGeneration
Licenseother
Transformers Version4.52.4
Torch Data Typebfloat16

Best Alternatives to MiniMax M3.1 Flash OQ4e Mtp

Best Alternatives
Context / RAM
Downloads
Likes
MiniMax M3.1 Flash OQ3e Mtp0K / 194.3 GB4172
MiniMax M3.1 Flash OQ3.5e Mtp0K / 211.4 GB3102