Phi 4 4bit by mlx-community

 ยป  All LLMs  ยป  mlx-community  ยป  Phi 4 4bit   URL Share it on

Phi 4 4bit is an open-source language model by mlx-community. Features: 2.3b LLM, VRAM: 8.2GB, Context: 16K, License: mit, Quantized, LLM Explorer Score: 0.19.

  4-bit   4bit   Base model:microsoft/phi-4 Base model:quantized:microsoft...   Chat   Code   Conversational   Custom code   En   Endpoints compatible   Math   Mlx   Phi   Phi3   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Phi 4 4bit 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 4bit (mlx-community/phi-4-4bit)
๐ŸŒŸ Advertise your project ๐Ÿš€

Phi 4 4bit Parameters and Internals

LLM NamePhi 4 4bit
Repository ๐Ÿค—https://huggingface.co/mlx-community/phi-4-4bit 
Base Model(s)  Phi 4   microsoft/phi-4
Model Size2.3b
Required VRAM8.2 GB
Updated2026-04-04
Maintainermlx-community
Model Typephi3
Model Files  5.3 GB: 1-of-2   2.9 GB: 2-of-2
Supported Languagesen
Quantization Type4bit
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length16384
Model Max Length16384
Transformers Version4.47.0
Tokenizer ClassGPT2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size100352
Torch Data Typebfloat16

Best Alternatives to Phi 4 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Phi 4 Mini Instruct 8bit128K / 4.1 GB2975
Phi 3.5 Mini Instruct 4bit128K / 2.1 GB31759
Numind NuExtract 1.5 MLX 8bit128K / 4.1 GB122
...hi 3 Medium 128K Instruct 4bit128K / 7.8 GB232
...m 128K Instruct 8.0bpw H8 EXL2128K / 13.4 GB44
...m 128K Instruct 6.0bpw H6 EXL2128K / 10.7 GB83
...dium 128K Instruct 8 0bpw EXL2128K / 13.4 GB01
...m 128K Instruct 3.0bpw H6 EXL2128K / 5.6 GB50
...m 128K Instruct 5.0bpw H6 EXL2128K / 8.9 GB50
Phi 3 Mini 128K Instruct 8bit128K / 4.1 GB5510
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/phi-4-4bit.

Rank the Phi 4 4bit 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? 52721 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum โ€” our secure, self-hosted AI agent for server management.
Release v20260328a