LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Phi 4 Bnb 4bit by unsloth

 »  All LLMs  »  unsloth  »  Phi 4 Bnb 4bit   URL Share it on

  37739   
  Arxiv:2412.08905   4-bit   4bit   Autotrain compatible   Base model:microsoft/phi-4 Base model:quantized:microsoft...   Bitsandbytes   Chat   Code   Conversational   En   Endpoints compatible   Llama   Math   Phi   Phi4   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/phi-4-bnb-4bit 

Phi 4 Bnb 4bit Benchmarks

MMLU Pro: 47.29
GPQA: 11.74
MUSR: 8.42
BBH: 53.54
IFEval: 67.3 vs 88 (so35)-23.5%
MATH Lvl 5: 46.07
LLME Score: 0.44582
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 4 Bnb 4bit (unsloth/phi-4-bnb-4bit)

Phi 4 Bnb 4bit Parameters and Internals

LLM NamePhi 4 Bnb 4bit
Repository 🤗https://huggingface.co/unsloth/phi-4-bnb-4bit 
Base Model(s)  Phi 4   microsoft/phi-4
Model Size8.1b
Required VRAM9.1 GB
Updated2025-03-12
Maintainerunsloth
Model Typellama
Model Files  5.0 GB: 1-of-2   4.1 GB: 2-of-2
Supported Languagesen
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length16384
Model Max Length16384
Transformers Version4.47.1
Tokenizer ClassGPT2Tokenizer
Padding Token<|dummy_87|>
Vocabulary Size100352
Torch Data Typebfloat16

Quantized Models of the Phi 4 Bnb 4bit

Model
Likes
Downloads
VRAM
DeepThinkers Phi4329029 GB
DeepThink Phi412429 GB
Phi 4 14B Grpo Limo04029 GB
Phi 4 14B Grpo Gsm8k 3e03129 GB
...APhi4 GRPO 250218 Merged 16bit01029 GB

Best Alternatives to Phi 4 Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
0 Roleplay4K / 9.6 GB204

Rank the Phi 4 Bnb 4bit 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? 44902 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.
Release v20241227
  Support LLM Explorer