Ploba logo

Find the right AI tool for the job: apps, agents, APIs, MCP servers and datasets, explained plainly.

Get the AI Digest

Discover

  • Explore
  • Top Charts
  • Categories
  • Agents
  • MCP servers
  • Developer tools

Learn & community

  • Learn AI
  • AI Glossary
  • Blog
  • Hackathons
  • People
  • AI Digest

For makers

  • List your tool
  • Docs
  • Claim a listing
  • Advertise
  • Write for us

Company

  • About
  • Careers
  • Changelog
  • Trust
  • Security
  • Contact

© 2026 Ploba. All rights reserved.

  • Privacy
  • Terms
  • Cookies
  • Advertising
  • All policies
llms.txt
Ploba logo
DiscoverHackathonsPeopleLearnAI Digest
Sign inGet started
HomeTop ChartsExploreCategories
TypesWeb apps1,894Agents585Plugins416APIs376Mobile apps152Datasets85
AdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise hereAdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise here
  1. Explore
  2. /
  3. Developer Tools
  4. /
  5. BiomedCLIP
Developer Tools
BiomedCLIP icon

BiomedCLIP

by Microsoft Research

BiomedCLIP is a biomedical vision-language model from Microsoft, pretrained on 15 million figure-caption pairs from PubMed Central. It supports retrieval, image classification and visual question answering research.

Web app·Free

View on Hugging Face(opens in a new tab)

About BiomedCLIP

Key features of BiomedCLIP

  • Pretrained on 15 million figure-caption pairs
  • PubMedBERT text encoder and Vision Transformer image encoder
  • Zero-shot image classification
  • Cross-modal retrieval
  • Visual question answering research
  • Loads through OpenCLIP from the Hugging Face hub or local files
  • Open data pipeline for PMC-15M

Who BiomedCLIP is for

  • AI researchers in biomedical vision-language work
  • Radiology and medical imaging researchers
  • Teams reproducing the published experiments

How to use BiomedCLIP

  1. 1

    Step 1: Create a Python 3.10 environment and install open_clip_torch and transformers as the card lists.

  2. 2

    Step 2: Load the model with create_model_from_pretrained from the Hugging Face hub path.

  3. 3

    Step 3: Write text labels such as chest X-ray or brain MRI and tokenize them.

  4. 4

    Step 4: Preprocess your images and compare image and text features to rank labels.

  5. 5

    Step 5: Keep use to research, as the intended use section requires.

BiomedCLIP FAQ

What data was it trained on?

PMC-15M, 15 million figure-caption pairs from PubMed Central articles. It covers image types such as microscopy, radiography and histology.

Can I use it in a clinical or commercial product?

No. The card says any deployed use, commercial or otherwise, is out of scope, and the model is meant for research only.

Can I use my own local copy?

Yes. The card shows how to download the weights and config with the Hugging Face hub and load them from local files.

What tasks does it handle?

The card lists cross-modal retrieval, image classification and visual question answering.

Details

Pricing
FreeReleased under the MIT license on Hugging Face. The card limits use to research and rules out deployed use.
Type
Web app
Categories
Developer ToolsHealth
Added
Sep 16, 2026
Microsoft Research iconPublisherMicrosoft Research

Built from public sources

We put this page together from BiomedCLIP’s own website and docs so you can compare it with other tools. Ploba isn’t affiliated with BiomedCLIP.

Work at BiomedCLIP? Claim the listing to manage it yourself.

Something wrong here?

More from Microsoft Research

View publisher
MatterGen iconMatterGenMicrosoft Research · FreeMatterGen is a generative model from Microsoft for designing inorganic materials across the periodic table. It can be fine-tuned to steer generation toward property constraints.Developer Tools · FreeMatterSim iconMatterSimMicrosoft Research · FreeMatterSim is a deep learning atomistic model that works across elements, temperatures and pressures. It is distributed as a Python package with pre-trained models.Developer Tools · FreeAurora iconAuroraMicrosoft Research · FreeAurora uses AI for AI foundation model for Earth-system prediction across weather, air quality, ocean, and environmental forecasting tasks.Data · Free

Related tools

See more
PubMedCLIP iconPubMedCLIPArizona State University · FreeMedical vision-language model adapting CLIP to radiology and biomedical image-text understandingDeveloper Tools · FreeSAM-Med2D iconSAM-Med2DOpenGVLab · FreeSAM-Med2D is an open-source adaptation of the Segment Anything Model for 2D medical image segmentation. It was fine-tuned on a dataset of 4.6M images and 19.7M masks.Developer Tools · FreeTotalSegmentator iconTotalSegmentatorUniversity Hospital Basel · FreeTotalSegmentator segments most major anatomical structures in any CT or MR image. It runs from the command line and was created at University Hospital Basel.Developer Tools · Free