Phi 4 Mini Instruct by microsoft

 ยป  All LLMs  ยป  microsoft  ยป  Phi 4 Mini Instruct   URL Share it on

  Arxiv:2503.01743   Ar   Autotrain compatible   Code   Conversational   Cs   Custom code   Da   De   En   Endpoints compatible   Es   Fi   Fr   He   Hu   Instruct   It   Ja   Ko   Multilingual   Nl   No   Phi3   Pl   Pt   Region:us   Ru   Safetensors   Sharded   Sv   Tensorflow   Th   Tr   Uk   Zh

Phi 4 Mini Instruct Benchmarks

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 (microsoft/Phi-4-mini-instruct)
๐ŸŒŸ Advertise your project ๐Ÿš€

Phi 4 Mini Instruct Parameters and Internals

LLM NamePhi 4 Mini Instruct
Repository ๐Ÿค—https://huggingface.co/microsoft/Phi-4-mini-instruct 
Model Size3.8b
Required VRAM7.7 GB
Updated2025-06-16
Maintainermicrosoft
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 Version4.45.0
Tokenizer ClassGPT2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size200064
Torch Data Typebfloat16

Quantized Models of the Phi 4 Mini Instruct

Model
Likes
Downloads
VRAM
Phi 4 Mini Instruct GGUF42121981 GB
Phi 4 Mini Instruct GGUF40106451 GB
...Mini Instruct Unsloth Bnb 4bit1539713 GB
Phi 4 Mini Instruct Bnb 4bit029032 GB
Phi 4 Mini Instruct 8bit318314 GB

Best Alternatives to Phi 4 Mini Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3.5 Mini Instruct128K / 7.7 GB276132876
Phi 3 Mini 128K Instruct128K / 7.7 GB3322061648
NuExtract V1.5128K / 7.7 GB10851189
NuExtract 1.5128K / 7.7 GB24309232
Phi 4 Mini Instruct128K / 7.7 GB451416
Phi 3.5 Mini TitanFusion 0.1128K / 7.7 GB250
Phi 4 Bifrost Sol 3.8B128K / 7.7 GB611
ECE EIFFEL 3Bv2128K / 7.7 GB50
Glider128K / 15.4 GB139041
Artemide 3.5128K / 7.7 GB97013

Rank the Phi 4 Mini Instruct Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 48168 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124