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

Borea Phi 3.5 Mini Instruct Coding by AXCXEPT

 »  All LLMs  »  AXCXEPT  »  Borea Phi 3.5 Mini Instruct Coding   URL Share it on

  6   

Borea Phi 3.5 Mini Instruct Coding is an open-source language model by AXCXEPT. Features: 3.8b LLM, VRAM: 7.7GB, Context: 128K, License: mit, Instruction-Based, LLM Explorer Score: 0.15.

  Conversational   Custom code   En   Endpoints compatible   Instruct   Ja   Phi3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/AXCXEPT/Borea-Phi-3.5-mini-Instruct-Coding 

Borea Phi 3.5 Mini Instruct Coding Benchmarks

LLME Score: 0.14652
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Borea Phi 3.5 Mini Instruct Coding (AXCXEPT/Borea-Phi-3.5-mini-Instruct-Coding)
🌟 Advertise your project 🚀

Borea Phi 3.5 Mini Instruct Coding Parameters and Internals

Model Type 
text generation, conversational
Use Cases 
Areas:
research, general applications
Primary Use Cases:
Coding, Extraction in Japanese language
Additional Notes 
This model is experimental and intended for research purposes.
Supported Languages 
ja (High proficiency), en (Unsure, but present)
Training Details 
Data Sources:
Japanese Wikipedia, FineWeb
Methodology:
Plain instruction tuning method
Hardware Used:
H100PCIe × 8
Input Output 
Accepted Modalities:
text
LLM NameBorea Phi 3.5 Mini Instruct Coding
Repository 🤗https://huggingface.co/AXCXEPT/Borea-Phi-3.5-mini-Instruct-Coding 
Model Size3.8b
Required VRAM7.7 GB
Updated2026-05-26
MaintainerAXCXEPT
Model Typephi3
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.7 GB: 2-of-2
Supported Languagesja en
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.43.0
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Borea Phi 3.5 Mini Instruct Coding

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3.5 Mini Instruct128K / 7.7 GB701846980
Phi 4 Mini Instruct Heretic128K / 7.7 GB4590
Phi 3 Mini 128K Instruct128K / 7.7 GB50
MediPhi Instruct128K / 7.7 GB170467
NuExtract V1.5128K / 7.7 GB10851189
Phi 3.5 Mini TitanFusion 0.1128K / 7.7 GB140
ECE EIFFEL 3Bv2128K / 7.7 GB50
Phi 4 Mini Instruct128K / 7.7 GB428524
MediPhi128K / 7.7 GB373923
MediPhi Clinical128K / 7.7 GB26614
Note: green Score (e.g. "73.2") means that the model is better than AXCXEPT/Borea-Phi-3.5-mini-Instruct-Coding.

Rank the Borea Phi 3.5 Mini Instruct Coding 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? 53972 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