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 3 12B It Qat Abliterated by mlabonne

 »  All LLMs  »  mlabonne  »  Gemma 3 12B It Qat Abliterated   URL Share it on

  124   

Gemma 3 12B It Qat Abliterated is an open-source language model by mlabonne. Features: 12b LLM, VRAM: 47.2GB, Context: 128K, License: gemma, Quantized, LLM Explorer Score: 0.2.

Base model:finetune:google/gem... Base model:google/gemma-3-12b-...   Conversational   Endpoints compatible   Gemma3 text   Image-text-to-text   Q4   Q4 0   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlabonne/gemma-3-12b-it-qat-abliterated 

Gemma 3 12B It Qat Abliterated Benchmarks

LLME Score: 0.20282
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gemma 3 12B It Qat Abliterated (mlabonne/gemma-3-12b-it-qat-abliterated)
🌟 Advertise your project 🚀

Gemma 3 12B It Qat Abliterated Parameters and Internals

LLM NameGemma 3 12B It Qat Abliterated
Repository 🤗https://huggingface.co/mlabonne/gemma-3-12b-it-qat-abliterated 
Base Model(s)  google/gemma-3-12b-it-qat-q4_0-unquantized   google/gemma-3-12b-it-qat-q4_0-unquantized
Model Size12b
Required VRAM47.2 GB
Updated2026-04-17
Maintainermlabonne
Model Typegemma3_text
Model Files  5.0 GB: 1-of-10   4.8 GB: 2-of-10   5.0 GB: 3-of-10   4.9 GB: 4-of-10   5.0 GB: 5-of-10   4.9 GB: 6-of-10   5.0 GB: 7-of-10   4.9 GB: 8-of-10   5.0 GB: 9-of-10   2.7 GB: 10-of-10
Quantization Typeq4|q4_0
Model ArchitectureGemma3ForCausalLM
Licensegemma
Context Length131072
Model Max Length131072
Transformers Version4.51.3
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size262208
Torch Data Typefloat32

Best Alternatives to Gemma 3 12B It Qat Abliterated

Best Alternatives
Context / RAM
Downloads
Likes
GrayLine Gemma3 12B128K / 24.3 GB1602
...ranscription Fixer Gemma 3 12B128K / 24.3 GB101
GaMS3 12B Instruct128K / 23.4 GB34102
Typhoon2.1 Gemma3 12B128K / 23.4 GB1229819
YanoljaNEXT Rosetta 12B 2510128K / 25.4 GB12029
Typhoon2.1 Gemma3 12B128K / 23.4 GB161018
Gemma 3 12B It Abliterated V2128K / 47.2 GB89019
Nile Chat 12B128K / 23.4 GB40712
Gemma 3 Coldbrew Test1128K / 23.4 GB50
Gemma 3 Glitter 12B128K / 23.4 GB1397
Note: green Score (e.g. "73.2") means that the model is better than mlabonne/gemma-3-12b-it-qat-abliterated.

Rank the Gemma 3 12B It Qat 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? 53053 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