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

Phi 4 Mini Instruct Heretic by TitleOS

 »  All LLMs  »  TitleOS  »  Phi 4 Mini Instruct Heretic   URL Share it on

  423   

Phi 4 Mini Instruct Heretic is an open-source language model by TitleOS. Features: 3.8b LLM, VRAM: 7.7GB, Context: 128K, License: mit, Instruction-Based, LLM Explorer Score: 0.32.

  Arxiv:2503.01743   Abliterated   Ar   Code   Conversational   Cs   Custom code   Da   De   Decensored   En   Endpoints compatible   Es   Fi   Fr   He   Heretic   Hu   Instruct   It   Ja   Ko   Multilingual   Nl   No   Phi3   Pl   Pt   Region:us   Ru   Safetensors   Sharded   Sv   Tensorflow   Th   Tr   Uk   Uncensored   Zh
Model Card on HF 🤗: https://huggingface.co/TitleOS/Phi-4-mini-instruct-heretic 

Phi 4 Mini Instruct Heretic Benchmarks

LLME Score: 0.32464
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 4 Mini Instruct Heretic (TitleOS/Phi-4-mini-instruct-heretic)
🌟 Advertise your project 🚀

Phi 4 Mini Instruct Heretic Parameters and Internals

LLM NamePhi 4 Mini Instruct Heretic
Repository 🤗https://huggingface.co/TitleOS/Phi-4-mini-instruct-heretic 
Model Size3.8b
Required VRAM7.7 GB
Updated2026-04-20
MaintainerTitleOS
Model Typephi3
Instruction-BasedYes
Model Files  4.9 GB: 1-of-2   2.8 GB: 2-of-2
Supported Languagesar zh cs da nl en fi fr de he hu it ja ko no pl pt ru es sv th tr uk
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.57.6
Tokenizer ClassGPT2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size200064

Best Alternatives to Phi 4 Mini Instruct Heretic

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3.5 Mini Instruct128K / 7.7 GB291298909
MediPhi Instruct128K / 7.7 GB370865
Phi 3 Mini 128K Instruct128K / 7.7 GB50
NuExtract V1.5128K / 7.7 GB10851189
Phi 3.5 Mini TitanFusion 0.1128K / 7.7 GB50
Phi 4 Mini Instruct128K / 7.7 GB838124
ECE EIFFEL 3Bv2128K / 7.7 GB90
MediPhi Clinical128K / 7.7 GB42514
MediPhi MedCode128K / 7.7 GB2907
MediPhi PubMed128K / 7.7 GB14910
Note: green Score (e.g. "73.2") means that the model is better than TitleOS/Phi-4-mini-instruct-heretic.

Rank the Phi 4 Mini Instruct Heretic 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