ModelLLMsvv1

GatorTron

by University of Florida · open-source · Last verified 2026-03-17

GatorTron is a large-scale clinical language model developed by the University of Florida, trained on over 90 billion words from de-identified clinical notes from UF Health. It sets state-of-the-art performance on multiple clinical NLP benchmarks and is one of the largest models trained on real-world EHR data.

https://github.com/uf-hobi-informatics-lab/GatorTron ↗

C+

C+—Average

Adoption: CQuality: AFreshness: C+Citations: B+Engagement: F

Specifications

License: Apache 2.0
Pricing: open-source
Capabilities: clinical-ner, clinical-relation-extraction, medical-qa, ehr-text-classification
Integrations: Hugging Face, PyTorch
Use Cases: clinical information extraction, phenotyping from EHR notes, clinical trial eligibility screening, adverse drug event detection
API Available: Yes
Parameters: ~8.9B
Context Window: 512 tokens
Modalities: text
Training Cutoff: 2022
Tags: clinical, ehr, uf-health, transformer, medical-nlp
Added: 2026-03-17
Completeness: 100%

Index Score

50.8

Adoption

Quality

Freshness

Citations

Engagement

Explore the full AI ecosystem on Agents as a Service