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 Reasoning by unsloth

 »  All LLMs  »  unsloth  »  Phi 4 Reasoning   URL Share it on

  172   

Phi 4 Reasoning is an open-source language model by unsloth. Features: 14.7b LLM, VRAM: 29.4GB, Context: 32K, License: mit, LLM Explorer Score: 0.19.

Base model:finetune:microsoft/... Base model:microsoft/phi-4-rea...   Chat   Code   Conversational   En   Endpoints compatible   Math   Phi   Phi3   Reasoning   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/phi-4-reasoning 

Phi 4 Reasoning Benchmarks

LLME Score: 0.19274
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 4 Reasoning (unsloth/phi-4-reasoning)
🌟 Advertise your project 🚀

Phi 4 Reasoning Parameters and Internals

LLM NamePhi 4 Reasoning
Repository 🤗https://huggingface.co/unsloth/phi-4-reasoning 
Base Model(s)  microsoft/phi-4-reasoning   microsoft/phi-4-reasoning
Model Size14.7b
Required VRAM29.4 GB
Updated2026-04-24
Maintainerunsloth
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 Length32768
Model Max Length32768
Transformers Version4.52.0.dev0
Tokenizer ClassGPT2Tokenizer
Padding Token<|dummy_85|>
Vocabulary Size100352
Torch Data Typebfloat16

Best Alternatives to Phi 4 Reasoning

Best Alternatives
Context / RAM
Downloads
Likes
Phi 4 Reasoning Plus32K / 29.4 GB1616
Flashlight V1.116K / 29.4 GB50
Phi 4 RP V016K / 29.5 GB143
Phi4 Abliterated16K / 29.4 GB912
Microsoft Phi 416K / 29.4 GB15655
Phi 4 Abliterated16K / 29.4 GB1234
Phi 4 Open R1 Distill EZOv116K / 29.4 GB7320
EZO Phi 4 V2.90016K / 29.4 GB560
EZO Phi 4 V2.135016K / 29.4 GB420
... Supervisor 0326h100normV2iw0832K / 29.4 GB3110
Note: green Score (e.g. "73.2") means that the model is better than unsloth/phi-4-reasoning.

Rank the Phi 4 Reasoning 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? 53972 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