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

Phi 3 Medium 4K Instruct Ov Int4 by fakezeta

 »  All LLMs  »  fakezeta  »  Phi 3 Medium 4K Instruct Ov Int4   URL Share it on

  7   
  Autotrain compatible   Code   Conversational   Custom code   Endpoints compatible   Instruct   Multilingual   Openvino   Phi3   Region:us
Model Card on HF 🤗: https://huggingface.co/fakezeta/Phi-3-medium-4k-instruct-ov-int4 

Phi 3 Medium 4K Instruct Ov Int4 Benchmarks

LLME Score: 0.15627
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 3 Medium 4K Instruct Ov Int4 (fakezeta/Phi-3-medium-4k-instruct-ov-int4)
🌟 Advertise your project 🚀

Phi 3 Medium 4K Instruct Ov Int4 Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
Research, Commercial applications
Applications:
General purpose AI systems, Memory/compute constrained environments, Latency bound scenarios
Primary Use Cases:
Language and multimodal research, Building blocks for generative AI powered features
Limitations:
Not designed for all downstream purposes
Considerations:
Developers should consider common limitations and adhere to laws.
Additional Notes 
Optimized for 4K token context length. Quantum int4 ONNX versions available.
Supported Languages 
language (multilingual), proficiency (primary focus on English)
Training Details 
Data Sources:
Publicly available documents, High-quality educational data, Newly created synthetic data
Data Volume:
4.8 trillion tokens
Methodology:
Supervised fine-tuning and Direct Preference Optimization
Context Length:
4096
Training Time:
42 days
Hardware Used:
512 H100-80G GPUs
Model Architecture:
Dense decoder-only Transformer
Safety Evaluation 
Methodologies:
Safety post-training
Ethical Considerations:
Developers should mitigate accuracy, safety, and fairness risks
Responsible Ai Considerations 
Fairness:
The models may reinforce demeaning or negative stereotypes due to training data biases.
Transparency:
Developers should follow transparency best practices.
Accountability:
Developers are responsible for ensuring compliance with laws and regulations.
Mitigation Strategies:
Train with supervision and optimize for safety guidelines.
Input Output 
Input Format:
Text format suited for chat prompts.
Accepted Modalities:
text
Output Format:
Generated text
Performance Tips:
Ensure BOS token is included for more reliable results.
LLM NamePhi 3 Medium 4K Instruct Ov Int4
Repository 🤗https://huggingface.co/fakezeta/Phi-3-medium-4k-instruct-ov-int4 
Required VRAM0 GB
Updated2025-09-23
Maintainerfakezeta
Model Typephi3
Instruction-BasedYes
Model Files  0.0 GB   8.7 GB   0.0 GB
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length4096
Model Max Length4096
Transformers Version4.41.2
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064

Best Alternatives to Phi 3 Medium 4K Instruct Ov Int4

Best Alternatives
Context / RAM
Downloads
Likes
Phi 4 Mini Instruct ONNX GQA128K /  GB134
Phi 3.5 Mini Instruct Onnx128K /  GB106531
Phi 3.5 Mini Instruct Onnx Web128K /  GB206914
Phi 3 Mini 128K Instruct Onnx128K /  GB1111191
...i 3 Mini 128K Instruct Ov Int4128K / 2 GB60
...Medium 128K Instruct Onnx Cuda128K /  GB2123
... Medium 128K Instruct Onnx Cpu128K /  GB6311
...3 Mini 128K Instruct Asym Int4128K / 2.5 GB1220
...um 128K Instruct Onnx Directml128K /  GB145
Model1128K / 0.8 GB200
Note: green Score (e.g. "73.2") means that the model is better than fakezeta/Phi-3-medium-4k-instruct-ov-int4.

Rank the Phi 3 Medium 4K Instruct Ov Int4 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