LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

MiniMax M2 8bit by mlx-community

 »  All LLMs  »  mlx-community  »  MiniMax M2 8bit   URL Share it on

  371   

MiniMax M2 8bit is an open-source language model by mlx-community. Features: LLM, VRAM: 223GB, Context: 192K, License: mit, Quantized, LLM Explorer Score: 0.24.

  8-bit   8bit Base model:minimaxai/minimax-m... Base model:quantized:minimaxai...   Conversational   Minimax   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/MiniMax-M2-8bit 

MiniMax M2 8bit Benchmarks

LLME Score: 0.24184
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MiniMax M2 8bit (mlx-community/MiniMax-M2-8bit)
🌟 Advertise your project 🚀

MiniMax M2 8bit Parameters and Internals

LLM NameMiniMax M2 8bit
Repository 🤗https://huggingface.co/mlx-community/MiniMax-M2-8bit 
Base Model(s)  MiniMax M2   MiniMaxAI/MiniMax-M2
Required VRAM223 GB
Updated2026-03-28
Maintainermlx-community
Model Typeminimax
Model Files  4.6 GB: 1-of-47   5.2 GB: 2-of-47   5.2 GB: 3-of-47   5.2 GB: 4-of-47   5.2 GB: 5-of-47   5.2 GB: 6-of-47   5.2 GB: 7-of-47   5.2 GB: 8-of-47   5.2 GB: 9-of-47   5.2 GB: 10-of-47   5.2 GB: 11-of-47   5.2 GB: 12-of-47   5.2 GB: 13-of-47   5.2 GB: 14-of-47   5.2 GB: 15-of-47   5.2 GB: 16-of-47   5.2 GB: 17-of-47   5.2 GB: 18-of-47   5.2 GB: 19-of-47   5.2 GB: 20-of-47   5.2 GB: 21-of-47   5.2 GB: 22-of-47   5.2 GB: 23-of-47   5.2 GB: 24-of-47   5.2 GB: 25-of-47   5.2 GB: 26-of-47   5.2 GB: 27-of-47   5.2 GB: 28-of-47   5.2 GB: 29-of-47   5.2 GB: 30-of-47   5.2 GB: 31-of-47   5.2 GB: 32-of-47   5.2 GB: 33-of-47   5.2 GB: 34-of-47   5.2 GB: 35-of-47   5.2 GB: 36-of-47   5.2 GB: 37-of-47   5.2 GB: 38-of-47   5.2 GB: 39-of-47   5.2 GB: 40-of-47   5.2 GB: 41-of-47   5.2 GB: 42-of-47   5.2 GB: 43-of-47
Quantization Type8bit
Model ArchitectureMiniMaxM2ForCausalLM
Licensemit
Context Length196608
Model Max Length196608
Transformers Version4.46.1
Vocabulary Size200064

Best Alternatives to MiniMax M2 8bit

Best Alternatives
Context / RAM
Downloads
Likes
MiniMax M2.7 HLWQ Q5192K / 42 GB173
MiniMax M2 Mlx 8bit Gs32192K / 206.5 GB1142
MiniMax M2 4bit192K / 128.3 GB144910
MiniMax M2 5bit192K / 155.8 GB1272
MiniMax M2 6bit192K / 185.8 GB1072
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/MiniMax-M2-8bit.

Rank the MiniMax M2 8bit Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52832 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer