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

Gemma 4 31B It Abliterated by wangzhang

 »  All LLMs  »  wangzhang  »  Gemma 4 31B It Abliterated   URL Share it on

  4744   

Gemma 4 31B It Abliterated is an open-source language model by wangzhang. Features: 31b LLM, VRAM: 62.5GB, License: gemma, LLM Explorer Score: 0.33.

  Abliterated   Abliterix Base model:finetune:google/gem... Base model:google/gemma-4-31b-...   Direct-weight-editing   Gemma4   Llm-judge   Region:us   Safetensors   Sharded   Tensorflow   Uncensored   Vllm
Model Card on HF 🤗: https://huggingface.co/wangzhang/gemma-4-31B-it-abliterated 

Gemma 4 31B It Abliterated Benchmarks

LLME Score: 0.32786
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gemma 4 31B It Abliterated (wangzhang/gemma-4-31B-it-abliterated)
🌟 Advertise your project 🚀

Gemma 4 31B It Abliterated Parameters and Internals

LLM NameGemma 4 31B It Abliterated
Repository 🤗https://huggingface.co/wangzhang/gemma-4-31B-it-abliterated 
Base Model(s)  google/gemma-4-31B-it   google/gemma-4-31B-it
Model Size31b
Required VRAM62.5 GB
Updated2026-05-02
Maintainerwangzhang
Model Typegemma4
Model Files  49.9 GB: 1-of-2   12.6 GB: 2-of-2
Model ArchitectureGemma4ForConditionalGeneration
Licensegemma
Transformers Version5.6.2
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Gemma 4 31B It Abliterated

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 4 31B IT NVFP40K / 32.6 GB2227074459
Gemma 4 31B It0K / 62.6 GB4911917
G4 MeroMero 31B0K / 62.6 GB228743
Gemma 4 31B It Bf160K / 62.6 GB59007
Gemma4 GarnetV2 31B0K / 62.6 GB83412
Gemma 4 31B JANG 4M CRACK0K / 22.6 GB7874
Gemopus 4 31B It0K / 62.6 GB5838
Gemma4 Garnet 31B0K / 62.6 GB6369
Gemma 4 31B It Official0K / 62.6 GB1870
Gemma 31B Sft 2500K / 62.5 GB1490
Note: green Score (e.g. "73.2") means that the model is better than wangzhang/gemma-4-31B-it-abliterated.

Rank the Gemma 4 31B It 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? 53781 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