LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Phi 4 by microsoft

 »  All LLMs  »  microsoft  »  Phi 4   URL Share it on

  472943   
  Arxiv:2412.08905   Autotrain compatible   Chat   Code   Conversational   En   Endpoints compatible   Math   Phi   Phi3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/microsoft/phi-4 

Phi 4 Benchmarks

LMSys ELO: 1202 vs 1272 (so35)-5.5%
MMLU Pro: 47.63
GPQA: 20.81
MUSR: 23.79
BBH: 52.43
IFEval: 5.85 vs 88 (so35)-93.4%
MATH Lvl 5: 31.65
LLME Score: 0.63747
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 4 (microsoft/phi-4)

Phi 4 Parameters and Internals

LLM NamePhi 4
Repository 🤗https://huggingface.co/microsoft/phi-4 
Model Size14.7b
Required VRAM29.4 GB
Updated2025-06-01
Maintainermicrosoft
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
Supported Languagesen
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length16384
Model Max Length16384
Transformers Version4.47.0
Tokenizer ClassGPT2Tokenizer
Padding Token<|dummy_85|>
Vocabulary Size100352
Torch Data Typebfloat16

Quantized Models of the Phi 4

Model
Likes
Downloads
VRAM
Phi 4 Unsloth Bnb 4bit574520710 GB
Phi 4 Bnb 4bit16109479 GB
Parm 2 CoT 14B 16K O1 QwQ72729 GB
Phi 4 GGUF42464705 GB
...perThoughts CoT 14B 16K O1 QwQ626529 GB
Phi 4 4bit199778 GB
Phi 4 8bit1326415 GB
Phi 4 6bit66711 GB

Best Alternatives to Phi 4

Best Alternatives
Context / RAM
Downloads
Likes
Phi 4 Reasoning Plus32K / 29.4 GB25266270
Phi 4 Reasoning32K / 29.4 GB35734184
Phi 4 Reasoning Plus32K / 29.4 GB2853
Flashlight V1.116K / 29.4 GB100
Phi4 Abliterated16K / 29.4 GB3212
Phi 4 RP V016K / 29.5 GB153
Phi 4 AbliteratedRP16K / 29.5 GB185
Microsoft Phi 416K / 29.4 GB30956
Phi 4 Abliterated16K / 29.4 GB3231
DNA R116K / 29.4 GB196737

Rank the Phi 4 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? 47753 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.
Release v20241227
  Support LLM Explorer