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 M2.1 by unsloth

 »  All LLMs  »  unsloth  »  MiniMax M2.1   URL Share it on

  35   

MiniMax M2.1 is an open-source language model by unsloth. Features: 228.7b LLM, VRAM: 75.2GB, Context: 192K, License: other, LLM Explorer Score: 0.37, ELO: 1364.

  Arxiv:2509.06501 Base model:minimaxai/minimax-m... Base model:quantized:minimaxai...   Conversational   Custom code   Endpoints compatible   Fp8   Minimax m2   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/MiniMax-M2.1 

MiniMax M2.1 Benchmarks

LMSys ELO: 1364 vs 1272 (so35)7.2%
LLME Score: 0.37004
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MiniMax M2.1 (unsloth/MiniMax-M2.1)
🌟 Advertise your project 🚀

MiniMax M2.1 Parameters and Internals

LLM NameMiniMax M2.1
Repository 🤗https://huggingface.co/unsloth/MiniMax-M2.1 
Base Model(s)  MiniMaxAI/MiniMax-M2.1   MiniMaxAI/MiniMax-M2.1
Model Size228.7b
Required VRAM75.2 GB
Updated2026-04-06
Maintainerunsloth
Model Typeminimax_m2
Model Files  3.7 GB: 0-of-130   1.2 GB: 1-of-130   2.5 GB: 2-of-130   1.2 GB: 3-of-130   2.5 GB: 4-of-130   1.2 GB: 5-of-130   2.5 GB: 6-of-130   1.2 GB: 7-of-130   2.5 GB: 8-of-130   1.2 GB: 9-of-130   2.5 GB: 10-of-130   1.2 GB: 11-of-130   2.5 GB: 12-of-130   1.2 GB: 13-of-130   2.5 GB: 14-of-130   1.2 GB: 15-of-130   2.5 GB: 16-of-130   1.2 GB: 17-of-130   2.5 GB: 18-of-130   1.2 GB: 19-of-130   2.5 GB: 20-of-130   1.2 GB: 21-of-130   2.5 GB: 22-of-130   1.2 GB: 23-of-130   2.5 GB: 24-of-130   1.2 GB: 25-of-130   2.5 GB: 26-of-130   1.2 GB: 27-of-130   2.5 GB: 28-of-130   1.2 GB: 29-of-130   2.5 GB: 30-of-130   1.2 GB: 31-of-130   2.5 GB: 32-of-130   1.2 GB: 33-of-130   2.5 GB: 34-of-130   1.2 GB: 35-of-130   2.5 GB: 36-of-130   1.2 GB: 37-of-130   2.5 GB: 38-of-130   1.2 GB: 39-of-130
Model ArchitectureMiniMaxM2ForCausalLM
Licenseother
Context Length196608
Model Max Length196608
Transformers Version4.57.3
Vocabulary Size200064

Best Alternatives to MiniMax M2.1

Best Alternatives
Context / RAM
Downloads
Likes
List 3.0 Ultra Coder Brain200K / 77.7 GB28000210
MiniMax M2.7 BF16200K / 147.3 GB5630
MiniMax M2.7192K / 75.2 GB5598841131
MiniMax M2192K / 77.7 GB1030201492
MiniMax M2.5192K / 74 GB7177431375
MiniMax M2.7192K / 213 GB25742
MiniMax M2.1192K / 77.7 GB373911276
MiniMax M2.5192K / 75.2 GB14035
MiniMax M2.7192K / 75.2 GB211017
MiniMax M2.7 RAM 100GB MLX192K / 100.4 GB27815
Note: green Score (e.g. "73.2") means that the model is better than unsloth/MiniMax-M2.1.

Rank the MiniMax M2.1 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? 53834 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