Gemma 3 4B It Abliterated V2 by mlabonne

 ยป  All LLMs  ยป  mlabonne  ยป  Gemma 3 4B It Abliterated V2   URL Share it on

  Autotrain compatible Base model:finetune:google/gem... Base model:google/gemma-3-4b-i...   Conversational   Endpoints compatible   Gemma3 text   Image-text-to-text   Region:us   Safetensors   Sharded   Tensorflow

Gemma 3 4B It Abliterated V2 Benchmarks

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

Gemma 3 4B It Abliterated V2 Parameters and Internals

LLM NameGemma 3 4B It Abliterated V2
Repository ๐Ÿค—https://huggingface.co/mlabonne/gemma-3-4b-it-abliterated-v2 
Base Model(s)  google/gemma-3-4b-it   google/gemma-3-4b-it
Model Size4b
Required VRAM15.5 GB
Updated2025-06-09
Maintainermlabonne
Model Typegemma3_text
Model Files  5.0 GB: 1-of-4   4.9 GB: 2-of-4   4.9 GB: 3-of-4   0.7 GB: 4-of-4
Model ArchitectureGemma3ForCausalLM
Licensegemma
Context Length131072
Model Max Length131072
Transformers Version4.51.3
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size262208
Torch Data Typefloat32
Gemma 3 4B It Abliterated V2 (mlabonne/gemma-3-4b-it-abliterated-v2)

Best Alternatives to Gemma 3 4B It Abliterated V2

Best Alternatives
Context / RAM
Downloads
Likes
Typhoon2.1 Gemma3 4B128K / 7.8 GB100864
Nile Chat 4B128K / 7.8 GB29413
Medgemma 4B It Abliterated128K / 7.8 GB2361
Gemma 3 4B Novision128K / 7.8 GB15571
Fallen Gemma3 4B V1128K / 8.6 GB6417
Gemma3 Vikhr 4B128K / 7.8 GB730
Gemma 3 Glitter 4B128K / 7.8 GB245
Amoral Gemma3 4B V2128K / 8.6 GB352
Amoral Gemma3 4B V1128K / 8.6 GB159615
Amoral Gemma3 4B128K / 8.6 GB3357
Note: green Score (e.g. "73.2") means that the model is better than mlabonne/gemma-3-4b-it-abliterated-v2.

Rank the Gemma 3 4B It Abliterated V2 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? 48023 in total.

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