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

Phi 3.5 Mini ITA by anakin87

 »  All LLMs  »  anakin87  »  Phi 3.5 Mini ITA   URL Share it on

  2287   

Phi 3.5 Mini ITA is an open-source language model by anakin87. Features: 3.8b LLM, VRAM: 7.7GB, Context: 128K, License: mit, Instruction-Based, LLM Explorer Score: 0.18.

  Arxiv:2406.06623 Base model:finetune:microsoft/... Base model:microsoft/phi-3.5-m...   Conversational   Custom code Dataset:efederici/capybara-cla...   Dataset:mlabonne/finetome-100k   En   Endpoints compatible   Instruct   It   Phi3   Region:us   Safetensors   Sharded   Spectrum   Tensorflow   Trl
Model Card on HF 🤗: https://huggingface.co/anakin87/Phi-3.5-mini-ITA 

Phi 3.5 Mini ITA Benchmarks

LLME Score: 0.17604
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 3.5 Mini ITA (anakin87/Phi-3.5-mini-ITA)
🌟 Advertise your project 🚀

Phi 3.5 Mini ITA Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
AI applications
Applications:
Chat applications, Text generation
Primary Use Cases:
Chat interface on Hugging Face Spaces
Additional Notes 
Fine-tuned for better performance in Italian. Compatible with HuggingFaceLocalGenerator and ChatGenerator components.
Supported Languages 
it (high), en (high)
Training Details 
Data Sources:
mlabonne/FineTome-100k, efederici/capybara-claude-15k-ita
Methodology:
Fine-tuning with Spectrum technique
Context Length:
128000
Training Time:
14 hours
Hardware Used:
A40 GPU
Input Output 
Input Format:
Text prompt
Accepted Modalities:
text
Output Format:
Generated text
Performance Tips:
Enable Flash Attention 2 for faster inference.
LLM NamePhi 3.5 Mini ITA
Repository 🤗https://huggingface.co/anakin87/Phi-3.5-mini-ITA 
Base Model(s)  microsoft/Phi-3.5-mini-instruct   microsoft/Phi-3.5-mini-instruct
Model Size3.8b
Required VRAM7.7 GB
Updated2026-01-21
Maintaineranakin87
Model Typephi3
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.7 GB: 2-of-2
Supported Languagesit en
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.44.2
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Phi 3.5 Mini ITA

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3.5 Mini Instruct128K / 7.7 GB291298909
MediPhi Instruct128K / 7.7 GB402465
NuExtract V1.5128K / 7.7 GB10851189
Phi 3 Mini 128K Instruct128K / 7.7 GB50
Phi 3.5 Mini TitanFusion 0.1128K / 7.7 GB50
Phi 4 Mini Instruct128K / 7.7 GB838124
ECE EIFFEL 3Bv2128K / 7.7 GB50
NuExtract 1.5128K / 7.7 GB4283245
MediPhi Clinical128K / 7.7 GB38513
MediPhi MedCode128K / 7.7 GB2087
Note: green Score (e.g. "73.2") means that the model is better than anakin87/Phi-3.5-mini-ITA.

Rank the Phi 3.5 Mini ITA 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? 52721 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