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

DeepThinkers Phi4 by EpistemeAI

 »  All LLMs  »  EpistemeAI  »  DeepThinkers Phi4   URL Share it on

  0   
  4bit   Autotrain compatible Base model:finetune:unsloth/ph... Base model:unsloth/phi-4-bnb-4...   Conversational   En   Endpoints compatible   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/EpistemeAI/DeepThinkers-Phi4 

DeepThinkers Phi4 Benchmarks

MMLU Pro: 47.31
GPQA: 12.08
MUSR: 8.02
BBH: 53.79
IFEval: 69.4 vs 88 (so35)-21.1%
MATH Lvl 5: 45.85
LLME Score: 0.32352
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DeepThinkers Phi4 (EpistemeAI/DeepThinkers-Phi4)
🌟 Advertise your project 🚀

DeepThinkers Phi4 Parameters and Internals

LLM NameDeepThinkers Phi4
Repository 🤗https://huggingface.co/EpistemeAI/DeepThinkers-Phi4 
Base Model(s)  Phi 4 Bnb 4bit   unsloth/phi-4-bnb-4bit
Model Size14.7b
Required VRAM29.4 GB
Updated2025-06-07
MaintainerEpistemeAI
Model Typellama
Model Files  4.9 GB: 1-of-6   5.0 GB: 2-of-6   4.9 GB: 3-of-6   5.0 GB: 4-of-6   5.0 GB: 5-of-6   4.6 GB: 6-of-6
Supported Languagesen
Gated ModelYes
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licenseproprietary
Context Length16384
Model Max Length16384
Transformers Version4.48.3
Tokenizer ClassGPT2Tokenizer
Padding Token<|dummy_87|>
Vocabulary Size100352
Torch Data Typebfloat16

Best Alternatives to DeepThinkers Phi4

Best Alternatives
Context / RAM
Downloads
Likes
DeepThink Phi416K / 29.4 GB241
Unaligned Thinker PHI 416K / 29.4 GB61
Phi 4 COT16K / 29.4 GB130
Samantha2.0 Phi4 Ita 16bit16K / 29.4 GB25920
...APhi4 GRPO 250218 Merged 16bit16K / 29.4 GB100
Phi4 New Params 16bit16K / 29.4 GB60
...i4.Turn.R1Distill V1.0 Tensors16K / 29.4 GB01
Phi 4 Llama T1 Full16K / 29.4 GB41
...kpoints 511 Onlytrainex Merged31K / 29.4 GB250
...ruct Extended 3500steps Merged31K / 29.4 GB710
Note: green Score (e.g. "73.2") means that the model is better than EpistemeAI/DeepThinkers-Phi4.

Rank the DeepThinkers Phi4 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? 51544 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 v20241124
  Support LLM Explorer