Qwen3 8B Abliterated by mlabonne

 ยป  All LLMs  ยป  mlabonne  ยป  Qwen3 8B Abliterated   URL Share it on

  Arxiv:1910.09700   Autotrain compatible   Conversational   Endpoints compatible   Qwen3   Region:us   Safetensors   Sharded   Tensorflow

Qwen3 8B Abliterated Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 8B Abliterated (mlabonne/Qwen3-8B-abliterated)

Qwen3 8B Abliterated Parameters and Internals

LLM NameQwen3 8B Abliterated
Repository ๐Ÿค—https://huggingface.co/mlabonne/Qwen3-8B-abliterated 
Model Size8b
Required VRAM16.4 GB
Updated2025-05-12
Maintainermlabonne
Model Typeqwen3
Model Files  4.9 GB: 1-of-4   4.9 GB: 2-of-4   5.0 GB: 3-of-4   1.6 GB: 4-of-4
Model ArchitectureQwen3ForCausalLM
Context Length40960
Model Max Length40960
Transformers Version4.51.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3 8B Abliterated

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 8B40K / 16.4 GB411323265
Qwen3 8B FP840K / 9.5 GB1526926
...iefied Qwen3 8B Abliterated V140K / 16.4 GB53365
Qwen3 8B40K / 16.4 GB61924
Smoothie Qwen3 8B40K / 16.4 GB1277
Qwen3 8B Esper340K / 32.7 GB317
...r0.0002 Pretrained 1e5 Epoch 240K / 16.4 GB350
Qwen3 8B Base32K / 16.4 GB1585325
Remnant Qwen3 8B32K / 16.4 GB411
Qwen3 8B Abliterated TIES32K / 16.4 GB191
Note: green Score (e.g. "73.2") means that the model is better than mlabonne/Qwen3-8B-abliterated.

Rank the Qwen3 8B Abliterated 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? 47272 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227