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

Sum Small by omi-health

 »  All LLMs  »  omi-health  »  Sum Small   URL Share it on

  197   

Sum Small is an open-source language model by omi-health. Features: 3.8b LLM, VRAM: 7.7GB, Context: 4K, License: mit, Instruction-Based, LLM Explorer Score: 0.14.

  Conversational   Custom code Dataset:omi-health/medical-dia...   En   Endpoints compatible   Instruct   Phi3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/omi-health/sum-small 

Sum Small Benchmarks

LLME Score: 0.13654
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Sum Small (omi-health/sum-small)
🌟 Advertise your project 🚀

Sum Small Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
research, AI-powered medical documentation
Primary Use Cases:
generation of SOAP summaries from medical dialogues
Limitations:
Synthetic data, not for direct clinical use
Considerations:
Integration with additional safety guardrails needed.
Supported Languages 
en (full-proficiency)
Training Details 
Data Sources:
Omi Health/medical-dialogue-to-soap-summary
Data Volume:
10,000 dialogues
Methodology:
fine-tuning
Hardware Used:
NVIDIA A100 GPUs
Responsible Ai Considerations 
Fairness:
Users are urged to consider ethical implications in healthcare use.
Transparency:
Model's synthetic training data composition.
Accountability:
Not directly accountable without safety validation.
LLM NameSum Small
Repository 🤗https://huggingface.co/omi-health/sum-small 
Model Size3.8b
Required VRAM7.7 GB
Updated2026-05-05
Maintaineromi-health
Model Typephi3
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.7 GB: 2-of-2
Supported Languagesen
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length4096
Model Max Length4096
Transformers Version4.41.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Sum Small

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3.5 Mini Instruct128K / 7.7 GB735393973
Phi 4 Mini Instruct Heretic128K / 7.7 GB4590
MediPhi Instruct128K / 7.7 GB270966
Phi 3 Mini 128K Instruct128K / 7.7 GB50
NuExtract V1.5128K / 7.7 GB10851189
Phi 3.5 Mini TitanFusion 0.1128K / 7.7 GB180
Phi 4 Mini Instruct128K / 7.7 GB719824
ECE EIFFEL 3Bv2128K / 7.7 GB80
MediPhi Clinical128K / 7.7 GB36414
MediPhi PubMed128K / 7.7 GB29311
Note: green Score (e.g. "73.2") means that the model is better than omi-health/sum-small.

Rank the Sum Small 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? 53591 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