Skip to main contentThe Local Bench

Biomedical · Google

TxGemma 9B chat

Hugging Face: google/txgemma-9b-chat · checked 2026-10-13

Therapeutics-development model (molecules, proteins, clinical-trial prediction).

Datasheet

Maker
Google
Parameters
9.24 BVerifiedsafetensors.total from the HF API Source
Licence
Health AI Developer Foundations termsVerified
Access
Gated: accept the terms on Hugging Face to download
Task (HF pipeline)
text-generation
First published on HF
2025-03-21
Last updated on HF
2025-04-10
Weights in memory
18 GB at 16-bit · 5.6 GB at ~4.85 bitsEstimateParameters × bits ÷ 8. Excludes context cache and runtime overhead; not every model has a 4-bit build.

Benchmark

Not yet measured
MedQA (4-option), accuracy

No comparable public score for this benchmark yet. We will not estimate one.

The description summarises the model card at https://huggingface.co/google/txgemma-9b-chat. Parameters and licence are read from the Hugging Face API; the weights-in-memory line is our arithmetic, not a measurement.