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 25B by ehristoforu

 »  All LLMs  »  ehristoforu  »  Phi 4 25B   URL Share it on

  5   

Phi 4 25B is an open-source language model by ehristoforu. Features: 25b LLM, VRAM: 49.8GB, Context: 16K, Merged, LLM Explorer Score: 0.29.

  Merged Model Base model:finetune:microsoft/...   Base model:microsoft/phi-4   Conversational   Custom code   Endpoints compatible   Phi3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ehristoforu/phi-4-25b 

Phi 4 25B Benchmarks

MMLU Pro: 48.34
GPQA: 9.17
MUSR: 11.43
BBH: 55.67
IFEval: 64.84 vs 88 (so35)-26.3%
MATH Lvl 5: 45.24
LLME Score: 0.28822
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 4 25B (ehristoforu/phi-4-25b)
🌟 Advertise your project 🚀

Phi 4 25B Parameters and Internals

LLM NamePhi 4 25B
Repository 🤗https://huggingface.co/ehristoforu/phi-4-25b 
Base Model(s)  Phi 4   microsoft/phi-4
Merged ModelYes
Model Size25b
Required VRAM49.8 GB
Updated2026-04-09
Maintainerehristoforu
Model Typephi3
Model Files  5.0 GB: 1-of-11   4.6 GB: 2-of-11   4.9 GB: 3-of-11   5.0 GB: 4-of-11   4.9 GB: 5-of-11   5.0 GB: 6-of-11   4.8 GB: 7-of-11   4.9 GB: 8-of-11   4.6 GB: 9-of-11   4.9 GB: 10-of-11   1.2 GB: 11-of-11
Model ArchitecturePhi3ForCausalLM
Context Length16384
Model Max Length16384
Transformers Version4.46.2
Tokenizer ClassGPT2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size100352
Torch Data Typebfloat16

Best Alternatives to Phi 4 25B

Best Alternatives
Context / RAM
Downloads
Likes
Sasando 1 25M0K / 0.1 GB91

Rank the Phi 4 25B 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? 52721 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