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 Vision Instruct by microsoft

 »  All LLMs  »  microsoft  »  Phi 3.5 Vision Instruct   URL Share it on

  1265584   

Phi 3.5 Vision Instruct is an open-source language model by microsoft. Features: 4.1b LLM, VRAM: 8.3GB, Context: 128K, License: mit, Instruction-Based, LLM Explorer Score: 0.32.

  Arxiv:2404.14219   Code   Conversational   Custom code   Image-text-to-text   Instruct   Multilingual   Phi3 v   Region:us   Safetensors   Sharded   Tensorflow   Vision
Model Card on HF 🤗: https://huggingface.co/microsoft/Phi-3.5-vision-instruct 

Phi 3.5 Vision Instruct Benchmarks

LLME Score: 0.31719
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 Vision Instruct (microsoft/Phi-3.5-vision-instruct)
🌟 Advertise your project 🚀

Phi 3.5 Vision Instruct Parameters and Internals

Model Type 
multimodal model, text generation, vision understanding
Use Cases 
Areas:
broad commercial, research use, English
Applications:
general purpose AI systems with visual and text input, Memory/compute constrained environments, Latency bound scenarios, General image understanding, Optical character recognition, Chart and table understanding, Multi-image comparison, Multi-image or video clip summarization
Primary Use Cases:
research on language and multimodal models, building block for generative AI powered features
Limitations:
models are not specifically designed or evaluated for all downstream purposes
Considerations:
Developers should consider common limitations of language models and ensure use complies with applicable laws.
Additional Notes 
Developers are responsible for mitigating biases and ensuring accuracy and safety in their use cases.
Supported Languages 
multilingual (primarily focused on English text)
Training Details 
Data Sources:
synthetic data, filtered publicly available websites, high-quality educational data, image-text interleave data, synthetic 'textbook-like' data for teaching math, coding, reasoning, etc., created multi-image and video data
Data Volume:
500B tokens
Methodology:
supervised fine-tuning and direct preference optimization
Context Length:
128000
Training Time:
6 days
Hardware Used:
256 A100-80G GPUs
Model Architecture:
includes image encoder, connector, projector, and Phi-3 Mini language model
Safety Evaluation 
Methodologies:
red teaming, adversarial conversation simulations, safety evaluation benchmark datasets
Risk Categories:
production of undesirable outputs across multiple risk categories
Ethical Considerations:
Leveraged human-labeled and synthetic datasets focusing on safety categories
Responsible Ai Considerations 
Fairness:
Limitations may still be present due to differing levels of representation of different groups or societal biases.
Transparency:
Developers should inform end-users that they are interacting with an AI system.
Accountability:
Developers are responsible for ensuring compliance with relevant laws and regulations.
Mitigation Strategies:
Apply responsible AI best practices, use safety classifiers or custom solutions, ensure transparency and accurate information.
Input Output 
Input Format:
Best suited for prompts using the chat format.
Accepted Modalities:
Text, Image
Output Format:
Generated text in response to input.
Performance Tips:
Set num_crops=4 for multi-frame and num_crops=16 for single-frame for best performance.
Release Notes 
Date:
August 2024
Notes:
Model enables multi-frame image understanding, improved single image benchmark performance, supports wider range of applications.
LLM NamePhi 3.5 Vision Instruct
Repository 🤗https://huggingface.co/microsoft/Phi-3.5-vision-instruct 
Model Size4.1b
Required VRAM8.3 GB
Updated2026-03-29
Maintainermicrosoft
Model Typephi3_v
Instruction-BasedYes
Model Files  4.9 GB: 1-of-2   3.4 GB: 2-of-2
Model ArchitecturePhi3VForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.38.1
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Phi 3.5 Vision Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3.5 Vision Instruct Bf16128K / 8.3 GB752
...28K Instruct Abliterated Alpha128K / 8.3 GB25117
...3 Vision Glaucoma Diagnosis V1128K / 8.3 GB171
Phi Charts Train Test Val128K / 8.3 GB50
... Vision 128K Instruct Onnx Cpu128K /  GB5328
...Vision 128K Instruct Onnx Cuda128K /  GB5427
...on 128K Instruct Onnx Directml128K /  GB558
...Vision 128K Instruct Quantized128K / 2.4 GB124
Phi 3.5 Vision Instruct 4bit128K / 2.3 GB3366
Phi 3.5 Vision Instruct 8bit128K / 4.4 GB763

Rank the Phi 3.5 Vision Instruct 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