multimodal LLM
MedGemma 1.5 4B
Update of MedGemma 4B (arXiv 2604.05081, 6 Apr 2026) adding 3D CT and MRI, whole-slide pathology, anatomical localization, longitudinal chest X-ray and document understanding. Reported gains over MedGemma 1 4B: MedQA +5%, EHRQA +22%, WSI macro F1 +47%, 3D MRI +11% (absolute or relative not stated).
Levelmodel
Classmultimodal LLM
Parameters4B
Contextnot in the notes
Released6 Apr 2026
Opennessopen weights restricted
Runs onnot in the notes
Statusnot in the notes
Lineage
finetunesuccessor
MedGemma 4B is the parent (successor)high confidencenotesWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 3 models. Confidence and evidence are the notes' own.
Industry Use Cases
R&D Topics
Identity
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- not in the notes
- Total parameters
- 4B sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- text, image, 3D
- Output
- text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights restricted
- Licence
- Health AI Developer Foundations terms of use sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- On premises or in the cloud (open weights).
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Links
DeveloperGooglebig tech, USA
Googlebig tech, USAModelMedGemma 1.5 4BGoogle, multimodal LLM
MedGemma 1.5 4BGoogle, multimodal LLMWho Runs Itnone recordedDeployments of these use cases; none names this model.
Organisations 1
Sources
- MedGemma 1.5 Technical Report arxiv.org https://arxiv.org/abs/2604.05081
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "MedGemma 1.5 4B", https://aurion.semai.id/models/google-medgemma-1-5-4b/, records of October 2026.