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

MiniMax M2 Mlx 8bit Gs32 by mlx-community

 »  All LLMs  »  mlx-community  »  MiniMax M2 Mlx 8bit Gs32   URL Share it on

  14   

MiniMax M2 Mlx 8bit Gs32 is an open-source language model by mlx-community. Features: 228.7b LLM, VRAM: 206.5GB, Context: 192K, License: mit, Quantized, LLM Explorer Score: 0.34, ELO: 1347.

  8-bit   8bit Base model:minimaxai/minimax-m... Base model:quantized:minimaxai...   Conversational   En   Minimax   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/MiniMax-M2-mlx-8bit-gs32 

MiniMax M2 Mlx 8bit Gs32 Benchmarks

LMSys ELO: 1347 vs 1272 (so35)5.9%
LLME Score: 0.34287
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MiniMax M2 Mlx 8bit Gs32 (mlx-community/MiniMax-M2-mlx-8bit-gs32)

MiniMax M2 Mlx 8bit Gs32 Parameters and Internals

LLM NameMiniMax M2 Mlx 8bit Gs32
Repository 🤗https://huggingface.co/mlx-community/MiniMax-M2-mlx-8bit-gs32 
Base Model(s)  MiniMax M2   MiniMaxAI/MiniMax-M2
Model Size228.7b
Required VRAM206.5 GB
Updated2026-07-27
Maintainermlx-community
Model Typeminimax
Model Files  4.9 GB: 1-of-54   5.3 GB: 2-of-54   4.3 GB: 3-of-54   5.3 GB: 4-of-54   4.3 GB: 5-of-54   5.3 GB: 6-of-54   4.3 GB: 7-of-54   5.3 GB: 8-of-54   4.3 GB: 9-of-54   5.3 GB: 10-of-54   4.3 GB: 11-of-54   5.3 GB: 12-of-54   4.3 GB: 13-of-54   5.3 GB: 14-of-54   4.3 GB: 15-of-54   5.3 GB: 16-of-54   4.3 GB: 17-of-54   5.3 GB: 18-of-54   4.3 GB: 19-of-54   5.3 GB: 20-of-54   4.3 GB: 21-of-54   5.3 GB: 22-of-54   4.3 GB: 23-of-54   5.3 GB: 24-of-54   4.3 GB: 25-of-54   5.3 GB: 26-of-54   4.3 GB: 27-of-54   5.3 GB: 28-of-54   4.3 GB: 29-of-54   5.3 GB: 30-of-54   4.3 GB: 31-of-54   5.3 GB: 32-of-54   4.3 GB: 33-of-54   5.3 GB: 34-of-54   4.3 GB: 35-of-54   5.3 GB: 36-of-54   4.3 GB: 37-of-54   5.3 GB: 38-of-54   4.3 GB: 39-of-54   5.3 GB: 40-of-54   4.3 GB: 41-of-54   5.3 GB: 42-of-54   4.3 GB: 43-of-54
Supported Languagesen
Quantization Type8bit
Model ArchitectureMiniMaxM2ForCausalLM
Licensemit
Context Length196608
Model Max Length196608
Transformers Version4.46.1
Vocabulary Size200064

Best Alternatives to MiniMax M2 Mlx 8bit Gs32

Best Alternatives
Context / RAM
Downloads
Likes
MiniMax M2.7 4bit Mxfp4192K / 121.5 GB135910
MiniMax M2.7 4bit192K / 128.3 GB7122
MiniMax M2.7 3bit192K / 99.7 GB4554
MiniMax M2.7 8bit Gs32192K / 211.8 GB2492
MiniMax M2.7 5bit192K / 155.8 GB1912
MiniMax M2.1 3bit192K / 99.7 GB35295
MiniMax M2.1 4bit192K / 128.3 GB24845
MiniMax M2.1 8bit192K / 217.8 GB22262
MiniMax M2.5 3bit192K / 99.7 GB41211
MiniMax M2.5 4bit192K / 128.3 GB2653
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/MiniMax-M2-mlx-8bit-gs32.

Rank the MiniMax M2 Mlx 8bit Gs32 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? 55446 in total.

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