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

Microsoft Phi 3 Medium 128K Instruct 8 0bpw EXL2 by Zoyd

 »  All LLMs  »  Zoyd  »  Microsoft Phi 3 Medium 128K Instruct 8 0bpw EXL2   URL Share it on

  2   

Microsoft Phi 3 Medium 128K Instruct 8 0bpw EXL2 is an open-source language model by Zoyd. Features: LLM, VRAM: 13.4GB, Context: 128K, License: mit, Quantized, Instruction-Based, LLM Explorer Score: 0.13.

  8-bit   Code   Conversational   Custom code   Endpoints compatible   Exl2   Instruct   Multilingual   Phi3   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Zoyd/microsoft_Phi-3-medium-128k-instruct-8_0bpw_exl2 

Microsoft Phi 3 Medium 128K Instruct 8 0bpw EXL2 Benchmarks

LLME Score: 0.13151
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Microsoft Phi 3 Medium 128K Instruct 8 0bpw EXL2 (Zoyd/microsoft_Phi-3-medium-128k-instruct-8_0bpw_exl2)
🌟 Advertise your project 🚀

Microsoft Phi 3 Medium 128K Instruct 8 0bpw EXL2 Parameters and Internals

Model Type 
text generation
Use Cases 
Applications:
General purpose AI systems, Research, Commercial applications
Primary Use Cases:
Memory/compute constrained environments, Latency bound scenarios, Strong reasoning: code, math, and logic
Limitations:
Models may not be suitable for high-risk scenarios without assessments.
Considerations:
Models are not specifically evaluated for all downstream purposes.
Additional Notes 
The Phi-3 Medium models can run on multiple platforms with optimized configurations through ONNX.
Supported Languages 
primary_language (English), other_languages ()
Training Details 
Data Sources:
Publicly available documents, High-quality educational data, Code, Newly created synthetic data, High quality chat format supervised data
Data Volume:
4.8 trillion tokens
Methodology:
Supervised fine-tuning (SFT) and Direct Preference Optimization (DPO)
Context Length:
128000
Training Time:
42 days
Hardware Used:
512 H100-80G GPUs
Model Architecture:
Dense decoder-only Transformer
Responsible Ai Considerations 
Fairness:
Models trained primarily on English text which affects other languages and dialects.
Transparency:
Developers are advised to follow transparency best practices.
Accountability:
Developers are responsible for ensuring compliance with relevant laws and regulations.
Mitigation Strategies:
Suggestions for using safety classifiers or custom solutions.
Input Output 
Input Format:
Chat format with user and assistant roles.
Accepted Modalities:
text
Output Format:
Generated text
LLM NameMicrosoft Phi 3 Medium 128K Instruct 8 0bpw EXL2
Repository 🤗https://huggingface.co/Zoyd/microsoft_Phi-3-medium-128k-instruct-8_0bpw_exl2 
Required VRAM13.4 GB
Updated2026-05-12
MaintainerZoyd
Model Typephi3
Instruction-BasedYes
Model Files  8.6 GB: 1-of-2   4.8 GB: 2-of-2
Quantization Typeexl2
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.39.3
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Microsoft Phi 3 Medium 128K Instruct 8 0bpw EXL2

Best Alternatives
Context / RAM
Downloads
Likes
Phi 4 Mini Instruct 8bit128K / 4.1 GB4146
Phi 4 Mini Instruct 6bit128K / 3.1 GB792
Phi 3.5 Mini Instruct 4bit128K / 2.1 GB19739
Phi 3.5 Mini Instruct 8bit128K / 4.1 GB1776
...m 128K Instruct 6.0bpw H6 EXL2128K / 10.7 GB1403
...m 128K Instruct 8.0bpw H8 EXL2128K / 13.4 GB974
...hi 3 Medium 128K Instruct 4bit128K / 7.8 GB552
...m 128K Instruct 3.0bpw H6 EXL2128K / 5.6 GB50
...m 128K Instruct 5.0bpw H6 EXL2128K / 8.9 GB50
Phi 3 Mini 128K Instruct 8bit128K / 4.1 GB6810
Note: green Score (e.g. "73.2") means that the model is better than Zoyd/microsoft_Phi-3-medium-128k-instruct-8_0bpw_exl2.

Rank the Microsoft Phi 3 Medium 128K Instruct 8 0bpw EXL2 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? 53999 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