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

Phi4 Abliterated by Undi95

 »  All LLMs  »  Undi95  »  Phi4 Abliterated   URL Share it on

  10   

Phi4 Abliterated is an open-source language model by Undi95. Features: 14.7b LLM, VRAM: 29.4GB, Context: 16K, LLM Explorer Score: 0.27.

  Custom code   Phi3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Undi95/Phi4-abliterated 

Phi4 Abliterated Benchmarks

LLME Score: 0.27273
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi4 Abliterated (Undi95/Phi4-abliterated)
🌟 Advertise your project 🚀

Phi4 Abliterated Parameters and Internals

LLM NamePhi4 Abliterated
Repository 🤗https://huggingface.co/Undi95/Phi4-abliterated 
Model Size14.7b
Required VRAM29.4 GB
Updated2026-07-09
MaintainerUndi95
Model Typephi3
Model Files  4.9 GB: 1-of-6   5.0 GB: 2-of-6   4.9 GB: 3-of-6   4.8 GB: 4-of-6   4.8 GB: 5-of-6   5.0 GB: 6-of-6
Model ArchitecturePhi3ForCausalLM
Context Length16384
Model Max Length16384
Transformers Version4.47.1
Tokenizer ClassGPT2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size100352
Torch Data Typebfloat16

Best Alternatives to Phi4 Abliterated

Best Alternatives
Context / RAM
Downloads
Likes
Phi 4 Reasoning Plus32K / 29.4 GB22029342
Phi 4 Reasoning32K / 29.4 GB21774228
Phi 4 Reasoning Plus32K / 29.4 GB566
Phi 4 Reasoning32K / 29.4 GB242
Phi 416K / 29.4 GB8330962251
Flashlight V1.116K / 29.4 GB50
Phi 4 RP V016K / 29.5 GB23
Microsoft Phi 416K / 29.4 GB8955
Phi 4 Abliterated16K / 29.4 GB2334
Phi 4 Open R1 Distill EZOv116K / 29.4 GB820
Note: green Score (e.g. "73.2") means that the model is better than Undi95/Phi4-abliterated.

Rank the Phi4 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? 54964 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