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

M51Lab MiniMax M2.7 REAP 139B A10B by dervig

 »  All LLMs  »  dervig  »  M51Lab MiniMax M2.7 REAP 139B A10B   URL Share it on

  1320   

M51Lab MiniMax M2.7 REAP 139B A10B is an open-source language model by dervig. Features: 139b LLM, VRAM: 205GB, Context: 192K, License: other, LLM Explorer Score: 0.31.

  Arxiv:2510.13999 Base model:finetune:minimaxai/... Base model:minimaxai/minimax-m...   Conversational   Custom code   Endpoints compatible   Minimax   Minimax m2   Moe   Pruning   Reap   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/dervig/m51Lab-MiniMax-M2.7-REAP-139B-A10B 

M51Lab MiniMax M2.7 REAP 139B A10B Benchmarks

LLME Score: 0.30708
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
M51Lab MiniMax M2.7 REAP 139B A10B (dervig/m51Lab-MiniMax-M2.7-REAP-139B-A10B)
🌟 Advertise your project 🚀

M51Lab MiniMax M2.7 REAP 139B A10B Parameters and Internals

LLM NameM51Lab MiniMax M2.7 REAP 139B A10B
Repository 🤗https://huggingface.co/dervig/m51Lab-MiniMax-M2.7-REAP-139B-A10B 
Base Model(s)  MiniMaxAI/MiniMax-M2.7   MiniMaxAI/MiniMax-M2.7
Model Size139b
Required VRAM205 GB
Updated2026-05-08
Maintainerdervig
Model Typeminimax_m2
Model Files  5.0 GB: 1-of-56   5.0 GB: 2-of-56   5.0 GB: 3-of-56   5.0 GB: 4-of-56   5.0 GB: 5-of-56   5.0 GB: 6-of-56   5.0 GB: 7-of-56   5.0 GB: 8-of-56   5.0 GB: 9-of-56   5.0 GB: 10-of-56   5.0 GB: 11-of-56   5.0 GB: 12-of-56   5.0 GB: 13-of-56   5.0 GB: 14-of-56   5.0 GB: 15-of-56   5.0 GB: 16-of-56   5.0 GB: 17-of-56   5.0 GB: 18-of-56   5.0 GB: 19-of-56   5.0 GB: 20-of-56   5.0 GB: 21-of-56   5.0 GB: 22-of-56   5.0 GB: 23-of-56   5.0 GB: 24-of-56   5.0 GB: 25-of-56   5.0 GB: 26-of-56   5.0 GB: 27-of-56   5.0 GB: 28-of-56   5.0 GB: 29-of-56   5.0 GB: 30-of-56   5.0 GB: 31-of-56   5.0 GB: 32-of-56   5.0 GB: 33-of-56   5.0 GB: 34-of-56   5.0 GB: 35-of-56   5.0 GB: 36-of-56   5.0 GB: 37-of-56   5.0 GB: 38-of-56   5.0 GB: 39-of-56   5.0 GB: 40-of-56   5.0 GB: 41-of-56
Model ArchitectureMiniMaxM2ForCausalLM
Licenseother
Context Length196608
Model Max Length196608
Transformers Version4.55.0
Vocabulary Size200064
Torch Data Typebfloat16

Best Alternatives to M51Lab MiniMax M2.7 REAP 139B A10B

Best Alternatives
Context / RAM
Downloads
Likes
...iMax M2.7 REAP 139B A10B NVFP4192K / 71.4 GB11966
MiniMax M2.5 REAP 139B A10B192K / 141.2 GB359726
MiniMax M2 REAP 139B A10B192K / 140.5 GB2218
Note: green Score (e.g. "73.2") means that the model is better than dervig/m51Lab-MiniMax-M2.7-REAP-139B-A10B.

Rank the M51Lab MiniMax M2.7 REAP 139B A10B 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? 53651 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