Qwen3 0.6B Gabliterated by Goekdeniz-Guelmez

 ยป  All LLMs  ยป  Goekdeniz-Guelmez  ยป  Qwen3 0.6B Gabliterated   URL Share it on

  Arxiv:2512.18901 Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3-0.6b Dataset:mlabonne/harmful behav... Dataset:mlabonne/harmless alpa...   Gabliteration   Model-index   Qwen3   Region:us   Safetensors   Uncensored

Qwen3 0.6B Gabliterated Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 0.6B Gabliterated (Goekdeniz-Guelmez/Qwen3-0.6B-gabliterated)
๐ŸŒŸ Advertise your project ๐Ÿš€

Qwen3 0.6B Gabliterated Parameters and Internals

LLM NameQwen3 0.6B Gabliterated
Repository ๐Ÿค—https://huggingface.co/Goekdeniz-Guelmez/Qwen3-0.6B-gabliterated 
Base Model(s)  Qwen/Qwen3-0.6B   Qwen/Qwen3-0.6B
Model Size0.6b
Required VRAM1.2 GB
Updated2026-03-14
MaintainerGoekdeniz-Guelmez
Model Typeqwen3
Model Files  1.2 GB   0.0 GB
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.57.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3 0.6B Gabliterated

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 Reranker 0.6B40K / 1.2 GB781059239
Qwen3 0.6B FP840K / 1.1 GB165812757
Qwen3 0.6B40K / 1.2 GB2925815
Qwen3 0.6B40K / 1.2 GB68293
Kimina Prover Distill 0.6B40K / 1.5 GB13441
OuteTTS 1.0 0.6B40K / 1.2 GB94290
Luth 0.6B Instruct40K / 1.2 GB2229
RStar Coder Qwen3 0.6B40K / 1.2 GB1737
PARD Qwen3 0.6B40K / 1.5 GB3731
Anonymizer 0.6B40K / 1.2 GB593
Note: green Score (e.g. "73.2") means that the model is better than Goekdeniz-Guelmez/Qwen3-0.6B-gabliterated.

Rank the Qwen3 0.6B Gabliterated Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 51631 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124