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 Instruct Onnx by microsoft

 »  All LLMs  »  microsoft  »  Phi 3.5 Mini Instruct Onnx   URL Share it on

  116   

Phi 3.5 Mini Instruct Onnx is an open-source language model by microsoft. Features: LLM, Context: 128K, License: mit, Instruction-Based, LLM Explorer Score: 0.16.

  Arxiv:2306.00978   Conversational   Custom code   Dml   Instruct   Onnx   Onnxruntime   Phi3   Region:us
Model Card on HF 🤗: https://huggingface.co/microsoft/Phi-3.5-mini-instruct-onnx 

Phi 3.5 Mini Instruct Onnx Benchmarks

LLME Score: 0.16118
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 Instruct Onnx (microsoft/Phi-3.5-mini-instruct-onnx)
🌟 Advertise your project 🚀

Phi 3.5 Mini Instruct Onnx Parameters and Internals

Model Type 
ONNX
Use Cases 
Areas:
commercial use, research
Applications:
general purpose AI systems
Primary Use Cases:
memory/compute constrained environments, latency bound scenarios, strong reasoning (especially code, math and logic)
Considerations:
Developers should consider common limitations of language models as they select use cases and evaluate and mitigate for accuracy, safety, and fairness.
Additional Notes 
Activation Aware Quantization (AWQ) works by identifying the top 1% most salient weights that are most important for maintaining accuracy and quantizing the remaining 99% of weights.
Training Details 
Data Sources:
synthetic data, filtered publicly available websites
Methodology:
supervised fine-tuning, proximal policy optimization, direct preference optimization
Context Length:
128000
Release Notes 
Version:
Phi-3.5-Mini-Instruct ONNX
Notes:
Update over the instruction-tuned Phi-3 Mini ONNX model release.
LLM NamePhi 3.5 Mini Instruct Onnx
Repository 🤗https://huggingface.co/microsoft/Phi-3.5-mini-instruct-onnx 
Updated2026-03-23
Maintainermicrosoft
Model Typephi3
Instruction-BasedYes
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.43.3
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Phi 3.5 Mini Instruct Onnx

Best Alternatives
Context / RAM
Downloads
Likes
Phi 4 Mini Instruct128K / 7.7 GB637798706
Phi 3 Mini 128K Instruct128K / 7.7 GB2475911696
Phi 3 Medium 128K Instruct128K / 28 GB4960387
Phi 4 Mini Instruct ONNX GQA128K /  GB365
Phi 3.5 Mini Instruct Onnx Web128K /  GB42415
Phi 3 Mini 128K Instruct Onnx128K /  GB97192
...i 3 Mini 128K Instruct Ov Int4128K / 2 GB50
...Medium 128K Instruct Onnx Cuda128K /  GB3923
... Medium 128K Instruct Onnx Cpu128K /  GB3913
...um 128K Instruct Onnx Directml128K /  GB305
Note: green Score (e.g. "73.2") means that the model is better than microsoft/Phi-3.5-mini-instruct-onnx.

Rank the Phi 3.5 Mini Instruct Onnx 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