Clinical LLM (Open Weights)

Fine-tuned decoder LLMs for clinical QA.

LLM multimodal LLM

5named models

580candidates

0deployments

0in Indonesia

Named Models

MedGemma 1.5 4BGoogleReleasedApr 2026Runs onnot in the notesClassmultimodal LLM

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).Commercial use: not stated; Jakarta hosting: unknown; Indonesian support: not stated

MedGemma 27B textGoogleReleasedMay 2025Runs onnot in the notesClassLLM27B text-only medical LLM built on Gemma 3 27B. Scores 87.7 on MedQA (0-shot with test-time scaling) per the MedGemma Technical Report.Commercial use: not stated; Jakarta hosting: unknown; Indonesian support: not stated

MedGemma 4BGoogleReleasednot in the notesRuns onnot in the notesClassmultimodal LLM

4B multimodal medical model built on Gemma 3 4B, used for radiology report generation and medical QA. Dermatology images among its inputs is unverified in the notes.Commercial use: not stated; Jakarta hosting: unknown; Indonesian support: not stated

Llama3-Med42-70BM42 HealthReleasedAug 2024Runs onnot in the notesClassLLM

70B clinical LLM fine-tuned from Llama3-70B Instruct; MedQA 79.10, MedMCQA 73.20, USMLE 83.80 (developer-reported).Commercial use: not stated; Jakarta hosting: unknown; Indonesian support: not stated

Llama3-Med42-8BM42 HealthReleasedAug 2024Runs onnot in the notesClassLLM

8B Med42 clinical LLM; MedQA 62.84 (developer-reported).Commercial use: not stated; Jakarta hosting: unknown; Indonesian support: not stated

Where this comes from

Models the research names for this use case. Research, with sources on each model record.

Who Runs It

No deployment is recorded for this use case.

Where this comes from

Documented uses by named organisations. The evidence column says who made the claim.

Candidate Models

MedQA

A general benchmark for this model class, not a test on this use case. Medical licensing-style multiple-choice QA. %. Higher is better.

MedGemma 27B textGoogle vendor-reported89.8

Med-PaLM 2Google vendor-reported86.5

Llama3-Med42-70BM42 Health vendor-reported79.1

MedGemma 4BGoogle vendor-reported64.4

Llama3-Med42-8BM42 Health vendor-reported62.84

Gemma 3 4BGoogle vendor-reported50.7

050100

MedMCQA

A general benchmark for this model class, not a test on this use case. Medical multiple-choice QA. %. Higher is better.

MedGemma 27B textGoogle vendor-reported74.2

Llama3-Med42-70BM42 Health vendor-reported73.2

050100

Nemotron-SEA-LION-v4.8-120B-A12BAI Singapore, LLMReleasedSep 2026open weightsIndonesian statedhas scoreslast 18 months

Nemotron-SEA-LION-v4.8-30B-A3BAI Singapore, LLMReleasedSep 2026open weightsIndonesian statedhas scoreslast 18 months

Apertus v1.5 70BSwiss AI (EPFL, ETH Zurich, CSCS), multimodal LLMReleasedSep 2026open weightsIndonesian statedhas scoreslast 18 months

Muse Glimmer 30BMeta, multimodal LLMReleasedAug 2026open weightsIndonesian statedhas scoreslast 18 months

Qwen-SEA-LION-v4.5-27B-ITAI Singapore, LLMReleasedMay 2026open weightsIndonesian statedhas scoreslast 18 months

Mistral Medium 3.5 (v26.04)Mistral AI, multimodal LLMReleasedApr 2026open weightsIndonesian statedhas scoreslast 18 months

Gemma 4 31BGoogle, Google DeepMind, multimodal LLMReleasedApr 2026open weightsIndonesian statedhas scoreslast 18 months

Qwen3.6-35B-A3BAlibaba (Qwen), LLMReleasedApr 2026open weightsruns on edgehas scoreslast 18 months

Qwen3.6-27BAlibaba (Qwen), multimodal LLMReleasedApr 2026open weightsIndonesian statedhas scoreslast 18 months

Qwen3.5-4BAlibaba (Qwen), multimodal LLMReleasedMar 2026open weightsruns on edgehas scoreslast 18 months

Showing 10 of 580. All models of this class

Where this comes from

Derived, not researched: models in the directory whose class matches a class this use case uses, excluding family records and models shut down or deprecated. Ranked by how many fit facts they meet, then by release date. Each fit fact is read from the model record.

Use Case

Industry: healthcare and pharma
Model classes: LLMmultimodal LLM
Benchmarks or datasets: MedQA MedMCQA PubMedQA MMLU Med AfriMed-QA AgentClinic-MedQA USMLE
Regulatory notes: FDA plans to identify and tag devices using foundation models, including LLMs.
Surat Edaran Menkominfo 9/2023 Etika Kecerdasan Artifisial, Kementerian Komunikasi dan Informatika (now Kementerian Komunikasi dan Digital)Clinical LLM (open weights) is an AI-based service run by an electronic system operator, and the circular asks such operators to build and use AI on the values of inclusivity, transparency, humanity and security.
UU 27/2022 Pelindungan Data Pribadi, DPR and President of the Republic of Indonesia (administered by Kementerian Komunikasi dan Digital)Clinical LLM (open weights) processes health data of patients, which the law treats as a specific category of personal data, so the controller needs a lawful basis, must protect the data and must honour data subject rights.
UU 17/2023 Kesehatan, DPR and President of the Republic of Indonesia (administered by Kementerian Kesehatan)Clinical LLM (open weights) is used in delivering health services or handling patient records, which this law governs through rules on medical records, health information systems, health technology and medical devices.

Where this comes from

From the industry tracks T08 to T10 of the research notes.

R&D Topics

Links to R&D topics are awaiting review.

Where this comes from

Which R&D topics would most change this use case. Drafted by Claude from the topic definitions and the use case; proposed until approved.

Opportunities

Opportunities are awaiting review.

Where this comes from

Gaps found by rule in what the directory holds for this use case. Each is a proposal for review.

Sources

MedGemma 1.5 Technical Report arxiv.org https://arxiv.org/abs/2604.05081
MedGemma Technical Report arxiv.org https://arxiv.org/html/2507.05201v2
google/medgemma-27b-text-it , Hugging Face huggingface.co https://huggingface.co/google/medgemma-27b-text-it
huggingface.co/m42-health/Llama3-Med42-70B https://huggingface.co/m42-health/Llama3-Med42-70B
List of Artificial Intelligence-Enabled Medical Devices fda.gov https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-enabled-medical-devices

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Clinical LLM (Open Weights)", https://aurion.semai.id/usecases/hc-clinical-llm-open/, records of October 2026.

Clinical LLM (Open Weights)

Named Models

Who Runs It

Candidate Models

MedQA

MedMCQA

Links

Models 5

Sources