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 M2.7 JANG 3L CRACK by dealignai

 »  All LLMs  »  dealignai  »  MiniMax M2.7 JANG 3L CRACK   URL Share it on

  562   

MiniMax M2.7 JANG 3L CRACK is an open-source language model by dealignai. Features: 25.6b LLM, VRAM: 29.3GB, Context: 192K, License: other, LLM Explorer Score: 0.36.

  Abliterated   Apple-silicon Base model:finetune:minimaxai/... Base model:minimaxai/minimax-m...   Conversational   Crack   Custom code   En   Jang   Ko   Minimax m2   Mixed-precision   Mlx   Moe   Quantized   Reasoning   Region:us   Safetensors   Sharded   Tensorflow   Uncensored   Zh
Model Card on HF 🤗: https://huggingface.co/dealignai/MiniMax-M2.7-JANG_3L-CRACK 

MiniMax M2.7 JANG 3L CRACK Benchmarks

LLME Score: 0.36455
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MiniMax M2.7 JANG 3L CRACK (dealignai/MiniMax-M2.7-JANG_3L-CRACK)
🌟 Advertise your project 🚀

MiniMax M2.7 JANG 3L CRACK Parameters and Internals

LLM NameMiniMax M2.7 JANG 3L CRACK
Repository 🤗https://huggingface.co/dealignai/MiniMax-M2.7-JANG_3L-CRACK 
Base Model(s)  MiniMaxAI/MiniMax-M2.7   MiniMaxAI/MiniMax-M2.7
Model Size25.6b
Required VRAM29.3 GB
Updated2026-04-13
Maintainerdealignai
Model Typeminimax_m2
Model Files  0.8 GB: 1-of-126   0.5 GB: 2-of-126   1.0 GB: 3-of-126   0.5 GB: 4-of-126   1.0 GB: 5-of-126   0.5 GB: 6-of-126   1.0 GB: 7-of-126   0.5 GB: 8-of-126   1.0 GB: 9-of-126   0.5 GB: 10-of-126   1.0 GB: 11-of-126   0.5 GB: 12-of-126   1.0 GB: 13-of-126   0.5 GB: 14-of-126   1.0 GB: 15-of-126   0.5 GB: 16-of-126   1.0 GB: 17-of-126   0.5 GB: 18-of-126   1.0 GB: 19-of-126   0.5 GB: 20-of-126   1.0 GB: 21-of-126   0.5 GB: 22-of-126   1.0 GB: 23-of-126   0.5 GB: 24-of-126   1.0 GB: 25-of-126   0.5 GB: 26-of-126   1.0 GB: 27-of-126   0.5 GB: 28-of-126   1.0 GB: 29-of-126   0.5 GB: 30-of-126   1.0 GB: 31-of-126   0.5 GB: 32-of-126   1.0 GB: 33-of-126   0.5 GB: 34-of-126   1.0 GB: 35-of-126   0.5 GB: 36-of-126   1.0 GB: 37-of-126   0.5 GB: 38-of-126   1.0 GB: 39-of-126
Supported Languagesen zh ko
Model ArchitectureMiniMaxM2ForCausalLM
Licenseother
Context Length196608
Model Max Length196608
Transformers Version4.46.1
Vocabulary Size200064

Best Alternatives to MiniMax M2.7 JANG 3L CRACK

Best Alternatives
Context / RAM
Downloads
Likes
MiniMax M2.7 JANG 3L192K / 29.3 GB10489
Note: green Score (e.g. "73.2") means that the model is better than dealignai/MiniMax-M2.7-JANG_3L-CRACK.

Rank the MiniMax M2.7 JANG 3L CRACK 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