LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Qwen3 4B Abliterated by mlabonne

 »  All LLMs  »  mlabonne  »  Qwen3 4B Abliterated   URL Share it on

  475   
  Abliterated   Abliteration   Autotrain compatible Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3-4b   Conversational   Endpoints compatible   Qwen3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlabonne/Qwen3-4B-abliterated 

Qwen3 4B Abliterated Benchmarks

LLME Score: 0.29541
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 4B Abliterated (mlabonne/Qwen3-4B-abliterated)

Qwen3 4B Abliterated Parameters and Internals

LLM NameQwen3 4B Abliterated
Repository 🤗https://huggingface.co/mlabonne/Qwen3-4B-abliterated 
Base Model(s)  Qwen/Qwen3-4B   Qwen/Qwen3-4B
Model Size4b
Required VRAM8.1 GB
Updated2025-05-31
Maintainermlabonne
Model Typeqwen3
Model Files  5.0 GB: 1-of-2   3.1 GB: 2-of-2
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3 4B Abliterated

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 4B FP840K / 5.2 GB2652622
Qwen3 4B40K / 8.1 GB181495
Qwen3 4B Esper340K / 16.1 GB52727
...iefied Qwen3 4B Abliterated V140K / 8.1 GB53510
Bootes Qwen3 Coder Reasoning40K / 8.1 GB2842
...iefied Qwen3 4B Abliterated V240K / 8.1 GB714
Jade Qwen3 4b40K / 8.1 GB480
BetaCeti Beta 4B Prime140K / 8.1 GB142
Crux Qwen3 OpenThinking 4B40K / 8.1 GB262
Jade Qwen 4b40K / 8.1 GB390
Note: green Score (e.g. "73.2") means that the model is better than mlabonne/Qwen3-4B-abliterated.

Rank the Qwen3 4B 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? 47753 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.
Release v20241227
  Support LLM Explorer