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

Mellum2 12B A2.5B Thinking Abliterated by josephmayo

 »  All LLMs  »  josephmayo  »  Mellum2 12B A2.5B Thinking Abliterated   URL Share it on

  30   

Mellum2 12B A2.5B Thinking Abliterated is an open-source language model by josephmayo. Features: 12b LLM, VRAM: 24.3GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.31.

  Abliteration Base model:finetune:jetbrains/... Base model:jetbrains/mellum2-1...   Conversational   Cot-steering   Endpoints compatible   Heretic-style   Jetbrains   Mellum   Mellum2   Moe   Per-expert   Per-layer   Projected-abliteration   Reasoning-model   Refusal-removal   Region:us   Safetensors   Sharded   Svd   Tensorflow   Thinking-model
Model Card on HF 🤗: https://huggingface.co/josephmayo/Mellum2-12B-A2.5B-Thinking-Abliterated 

Mellum2 12B A2.5B Thinking Abliterated Benchmarks

LLME Score: 0.31423
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mellum2 12B A2.5B Thinking Abliterated (josephmayo/Mellum2-12B-A2.5B-Thinking-Abliterated)
🌟 Advertise your project 🚀

Mellum2 12B A2.5B Thinking Abliterated Parameters and Internals

LLM NameMellum2 12B A2.5B Thinking Abliterated
Repository 🤗https://huggingface.co/josephmayo/Mellum2-12B-A2.5B-Thinking-Abliterated 
Base Model(s)  JetBrains/Mellum2-12B-A2.5B-Thinking   JetBrains/Mellum2-12B-A2.5B-Thinking
Model Size12b
Required VRAM24.3 GB
Updated2026-06-04
Maintainerjosephmayo
Model Typemellum
Model Files  3.7 GB: 1-of-7   3.9 GB: 2-of-7   3.6 GB: 3-of-7   3.9 GB: 4-of-7   3.6 GB: 5-of-7   3.9 GB: 6-of-7   1.7 GB: 7-of-7
Model ArchitectureMellumForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version5.10.0.dev0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Vocabulary Size98304

Best Alternatives to Mellum2 12B A2.5B Thinking Abliterated

Best Alternatives
Context / RAM
Downloads
Likes
Mellum2 12B A2.5B Thinking128K / 24.3 GB6938168
Mellum2 12B A2.5B Instruct128K / 24.3 GB141847
...m2 12B A2.5B Thinking Mlx 4bit128K / 7.3 GB1632
Note: green Score (e.g. "73.2") means that the model is better than josephmayo/Mellum2-12B-A2.5B-Thinking-Abliterated.

Rank the Mellum2 12B A2.5B Thinking Abliterated 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? 54290 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