scientificfamily
TxGemma
Google suite of efficient, generalist language models for therapeutic property prediction, with interactive reasoning and explanation in the chat versions. Paper by Wang et al. (2025).
Levelfamily
Classscientific
Parametersnot in the notes
Contextnot in the notes
Released25 Mar 2025
Opennessopen weights restricted
Runs onnot in the notes
Statusactive
Lineage
TxGemma 27B chat belongs to this familyscientific21 Mar 2025TxGemma 2B predict belongs to this familyscientific21 Mar 2025TxGemma 9B predict belongs to this familyscientific21 Mar 2025Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.
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
- dense transformer
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Note
- Published sizes include 2B and 9B predict models and a 27B chat model (Hugging Face).
- Context length
- not in the notes
- Input
- text, molecule
- 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
- not in the notes 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
- Gated on Hugging Face with licence tag "other"; the terms page was not opened.
- 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.
Industry Use Cases
No industry use case links this model.
Links
DeveloperGooglebig tech, USA
Googlebig tech, USAModelTxGemmaGoogle, scientific
TxGemmaGoogle, scientificR&D TopicsDomain Adaptation (Vertical Models)
Use CasesClinical LLM (Open Weights)HealthcareClinical LLM (Frontier Proprietary)HealthcareRadiology Report GenerationHealthcarePharma Documents, Regulatory and Life-Science R&DHealthcare+10 moreUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs It
Kementerian Kesehatan (Kemenkes), PusdatinPlanned, 19 Aug 2026
PT Pertamina Geothermal EnergyIn production, 14 Jul 2026
Banner HealthIn production, 11 Jan 2026CommureIn production, 11 Jan 2026+47 moreDeployments of these use cases; none names this model.
Kementerian Kesehatan (Kemenkes), PusdatinPlanned, 19 Aug 2026PT Pertamina Geothermal EnergyIn production, 14 Jul 2026Banner HealthIn production, 11 Jan 2026CommureIn production, 11 Jan 2026+47 moreDeployments of these use cases; none names this model.Models 3
Organisations 1
Sources
- arxiv.org/abs/2504.06196 https://arxiv.org/abs/2504.06196
- huggingface.co/google/txgemma-9b-predict https://huggingface.co/google/txgemma-9b-predict
- docs.cloud.google.com/gemini-enterprise-agent-platform/models/googl... https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/google-models
- developers.googleblog.com/en/introducing-txgemma-open-models-improving-... https://developers.googleblog.com/en/introducing-txgemma-open-models-improving-therapeutics-development/
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "TxGemma", https://aurion.semai.id/models/google-txgemma/, records of October 2026.