Phi 4 8bit by mlx-community

 ยป  All LLMs  ยป  mlx-community  ยป  Phi 4 8bit   URL Share it on

  8-bit   8bit   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 8bit 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 8bit (mlx-community/phi-4-8bit)
๐ŸŒŸ Advertise your project ๐Ÿš€

Phi 4 8bit Parameters and Internals

LLM NamePhi 4 8bit
Repository ๐Ÿค—https://huggingface.co/mlx-community/phi-4-8bit 
Base Model(s)  Phi 4   microsoft/phi-4
Model Size4.1b
Required VRAM15.6 GB
Updated2025-12-31
Maintainermlx-community
Model Typephi3
Model Files  5.3 GB: 1-of-3   5.4 GB: 2-of-3   4.9 GB: 3-of-3
Supported Languagesen
Quantization Type8bit
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 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Phi 4 Mini Instruct 8bit128K / 4.1 GB4954
...hi 3 Medium 128K Instruct 4bit128K / 7.8 GB452
...m 128K Instruct 8.0bpw H8 EXL2128K / 13.4 GB24
...m 128K Instruct 6.0bpw H6 EXL2128K / 10.7 GB53
...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
...28K Instruct Ov Fp16 Int4 Asym128K / 2.5 GB70
...128K Instruct HQQ 2bit Smashed128K / 1.4 GB80
...128K Instruct HQQ 4bit Smashed128K / 2.9 GB70
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/phi-4-8bit.

Rank the Phi 4 8bit 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? 51611 in total.

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