Granite 4.1 3B Abliterated AND Disinhibited by treadon

 »  All LLMs  »  treadon  »  Granite 4.1 3B Abliterated AND Disinhibited   URL Share it on

Granite 4.1 3B Abliterated AND Disinhibited is an open-source language model by treadon. Features: 3b LLM, VRAM: 6.8GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.26.

  Abliteration Base model:finetune:ibm-granit... Base model:ibm-granite/granite...   Conversational   Disinhibition   Endpoints compatible   Granite   Mechanistic-interpretability   Region:us   Safetensors

Granite 4.1 3B Abliterated AND Disinhibited Benchmarks

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

Granite 4.1 3B Abliterated AND Disinhibited Parameters and Internals

LLM NameGranite 4.1 3B Abliterated AND Disinhibited
Repository 🤗https://huggingface.co/treadon/granite-4.1-3b-Abliterated-AND-Disinhibited 
Base Model(s)  ibm-granite/granite-4.1-3b   ibm-granite/granite-4.1-3b
Model Size3b
Required VRAM6.8 GB
Updated2026-06-02
Maintainertreadon
Model Typegranite
Model Files  6.8 GB
Model ArchitectureGraniteForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version5.5.3
Tokenizer ClassGPT2Tokenizer
Padding Token<|pad|>
Vocabulary Size100352
Errorsreplace

Best Alternatives to Granite 4.1 3B Abliterated AND Disinhibited

Best Alternatives
Context / RAM
Downloads
Likes
Granite 4.1 3B128K / 6.8 GB16133675
Granite 4.1 3B Base128K / 6.8 GB5213917
Granite 4.1 3B128K / 6.8 GB26766
...ranite 4.1 3B SFT Fable5 Glint128K / 6.8 GB420
Granite 4.1 3B Mxfp4128K / 1.8 GB7583
... Claude Opus Reasoning Unsloth128K / 6.8 GB1113
Granite 4.1 3B Abliterated128K / 6.8 GB41
PowerLM 3B4K / 14 GB16256721
PowerLM 3B4K / 14 GB1158218
Granite 3B Mup Test Artifact4K / 14 GB1440
Note: green Score (e.g. "73.2") means that the model is better than treadon/granite-4.1-3b-Abliterated-AND-Disinhibited.

Rank the Granite 4.1 3B Abliterated AND Disinhibited 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? 54653 in total.

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