MedLM Models by Google DeepMind
Google DeepMindProprietary
2 models2023
About
Google's MedLM family of medical large language models, fine-tuned for healthcare and life science tasks. Available in medium and large variants on Vertex AI.
Archived Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
2 in view2 retired
MedLM MediumArchived
Keep only for existing workloads; choose a current variant for new builds.
2023-12medicalstructured outputs
MedLM LargeArchived
Keep only for existing workloads; choose a current variant for new builds.
2023-12medicalstructured outputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| MedLM Medium | Keep only for existing workloads; choose a current variant for new builds. | 2023-12 | medicalstructured outputs | Archived |
| MedLM Large | Keep only for existing workloads; choose a current variant for new builds. | 2023-12 | medicalstructured outputs | Archived |
Release Timeline
1 release group2023-12
2 retired
MedLM Large
Archivedmedicalstructured outputs
MedLM Medium
Archivedmedicalstructured outputs
Specifications(2 models)
| Model | Released | Structured Outputs |
|---|---|---|
| MedLM Medium | 2023-12 | Yes |
| MedLM Large | 2023-12 | Yes |
Available From(1 provider)
Frequently Asked Questions
- What is MedLM used for?
- MedLM is used for medical and structured outputs. The family description and listed model capabilities point to those workloads as the best fit.
- How does MedLM compare to Gemma 4?
- MedLM by Google DeepMind is strongest where you need medical, while Gemma 4 by Google DeepMind is the closest related family to check for vision and multimodal work. MedLM has 2 listed variants, while Gemma 4 reaches up to 256K context, so compare the specs and pricing tables before choosing a production model.
- Which MedLM model should I use?
- If price is the main constraint, use the pricing table first because MedLM does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate MedLM Medium with structured outputs.
