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

Phi3 Mini 4K Sft DPO Quant by matteosz

 »  All LLMs  »  matteosz  »  Phi3 Mini 4K Sft DPO Quant   URL Share it on

  5   

Phi3 Mini 4K Sft DPO Quant is an open-source language model by matteosz. Features: 2.1b LLM, VRAM: 2.3GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.14.

  4-bit   Autotrain compatible   Bitsandbytes   Conversational   Custom code   En   Endpoints compatible   Phi-3   Phi3   Quantization   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/matteosz/phi3-mini-4k-sft-dpo-quant 

Phi3 Mini 4K Sft DPO Quant Benchmarks

LLME Score: 0.13735
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi3 Mini 4K Sft DPO Quant (matteosz/phi3-mini-4k-sft-dpo-quant)
🌟 Advertise your project 🚀

Phi3 Mini 4K Sft DPO Quant Parameters and Internals

Model Type 
fine-tuned model, quantized model, STEM-focused model
Use Cases 
Areas:
education
Applications:
AI university tutor
Primary Use Cases:
Being an AI university tutor
Additional Notes 
This model has been quantized to 4 bits for efficiency using a specific BitsAndBytesConfig.
Supported Languages 
en (proficient)
Training Details 
Data Sources:
STEM domains
Methodology:
Fine-tuned with SFT and DPO
LLM NamePhi3 Mini 4K Sft DPO Quant
Repository 🤗https://huggingface.co/matteosz/phi3-mini-4k-sft-dpo-quant 
Model Size2.1b
Required VRAM2.3 GB
Updated2025-09-13
Maintainermatteosz
Model Typephi3
Model Files  2.3 GB
Supported Languagesen
Model ArchitecturePhi3ForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.41.1
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32011
Torch Data Typefloat16

Best Alternatives to Phi3 Mini 4K Sft DPO Quant

Best Alternatives
Context / RAM
Downloads
Likes
...xZSsgOijsAiwZBXCZaCeJGxXyjzVTt128K / 2.3 GB60
...guGNWodemktssFvRBlcJZUwVLDzmSa128K / 2.3 GB60
...uDtCRwSjaCHvWLsRNvYmzIBDUAuGnq128K / 2.3 GB60
Tiny Random Phi3ForCausalLM4K / 0 GB51670
NuExtract Finetuned4K / 2.8 GB60
Orpo Phi4K / 7.7 GB60
Quantized Phi 3 Mini 4K4K / 2.3 GB71
... 3 Mini 128K Instruct Bnb 4bit128K / 2.3 GB161
...3 Mini 4K Instruct 4bit 64rank4K / 2.4 GB60
...hi 3 Mini 4K Instruct Bnb 4bit4K / 2.3 GB80
Note: green Score (e.g. "73.2") means that the model is better than matteosz/phi3-mini-4k-sft-dpo-quant.

Rank the Phi3 Mini 4K Sft DPO Quant 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? 52758 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer