Government Of India
A-
A
A+
medgemma-27b-text-it
google/medgemma-27b-text-it
About Model
MedGemma is a collection of Gemma 3 variants that are trained for performance on medical text and image comprehension. Developers can use MedGemma to accelerate building healthcare-based AI applications. MedGemma currently comes in two variants: a 4B multimodal version and a 27B text-only version.
MedGemma 27B has been trained exclusively on medical text and optimized for inference-time computation. MedGemma 27B is only available as an instruction-tuned model.
MedGemma variants have been evaluated on a range of clinically relevant benchmarks to illustrate their baseline performance. These include both open benchmark datasets and curated datasets. Developers can fine-tune MedGemma variants for improved performance. Consult the Intended Use section below for more details.
A full technical report will be available soon.
medgemma-27b-text-it
Metadata
Other
Large Language Models
Transformers
Open
Healthcare, Wellness and Family Welfare
18/09/25 10:27:48
0
Activity Overview
0
5 
0 
863
Tags
- Transformers
- safetensors
- endpoints_compatible
- Text Generation
- text-generation-inference
- conversational
- autotrain_compatible
- medical
- region:us
- license:other
- gemma3_text
- clinical-reasoning
- thinking
- base_model:finetune:google/gemma-3-27b-pt
- arxiv:2303.15343
- arxiv:2501.19393
- arxiv:2411.15640
- arxiv:2501.18362
- base_model:google/gemma-3-27b-pt
- arxiv:2404.05590
- arxiv:2009.13081
- arxiv:2102.09542
License Control
Other
More Models from Google LLC
TimesFM 3 PyTorch
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
GNM Generative aNthropometric Model - v3
GNM (pronounced genome) is a state-of-the-art parametric 3D statistical model of the human head developed by Google. Learned from a large dataset of high-resolution 3D scans, GNM provides fine-grained, disentangled control over facial identity, expressions, and head pose, complete with controllable internal anatomy (eyeballs, teeth, and tongue).
The model is released under the Apache 2.0 permissive license, suitable for both academic research and commercial applications.
mesh
3d
3dmm
computer vision
head-tracking
digital-humans
parametric-model
human-head
- 0
- 0
- 0
3
Updated Today
Gemma-4-12B-it-assistant
This model card is for the Multi-Token Prediction (MTP) drafters for the Gemma 4 models. MTP is implemented by extending the base model with a smaller, faster draft model. When used in a Speculative Decoding pipeline, the draft model predicts several tokens ahead, which the target model then verifies in parallel. This results in significant decoding speedups (up to 3x) while guaranteeing the exact same quality as standard generation, making these checkpoints perfect for low-latency and ODML.
Transformers
license:apache-2.0
arxiv:2607.02770
gemma4_unified_assistant
region:us
any-to-any
Text Generation
endpoints_compatible
safetensors
- 0
- 0
- 0
- 3
Updated Today
TIPS Text-Image Pre-training with Spatial awareness ICLR 2025
TIPS (Text-Image Pre-training with Spatial awareness, ICLR 2025) is a family of contrastive vision-language models that produce spatially rich image features aligned with text embeddings. This is the original (v1) g/14 release with 1.1B vision params and 389M text params, converted from the official checkpoints.
Feature Extraction
arxiv:2410.16512
zero-shot
contrastive-learning
image-text
vision
- 0
- 0
- 0
- 3
Updated Today
DiffusionGemma
DiffusionGemma is a generative model built by Google DeepMind. Based on the 26B A4B Mixture-of-Experts (MoE) Gemma 4 architecture, DiffusionGemma generates tokens using discrete diffusion. This open-weights model is multimodal, handling text, image, and video inputs to generate text output.
region:us
conversational
image-text-to-text
endpoints_compatible
safetensors
Transformer
license:apache-2.0
deploy:sagemaker
diffusion_gemma
Public Space AI
google
- 1
- 3
- 0
- 34
Updated 10 day(s) ago
google/embeddinggemma-300m-qat-q8_0-unquantized
google/embeddinggemma-300m-qat-q8_0-unquantized
gemma3_text
autotrain_compatible
Sentence Similarity
endpoints_compatible
safetensors
Feature Extraction
region:us
sentence-transformers
license:gemma
- 0
- 2
- 0
- 314
Updated 1 year(s) ago
txgemma-27b-chat
google/txgemma-27b-chat
conversational
Transformers
safetensors
endpoints_compatible
Text Generation
text-generation-inference
en
autotrain_compatible
gemma2
region:us
license:other
therapeutics
drug-development
arxiv:2406.06316
arxiv:2504.06196
- 0
- 8
- 0
- 242
Updated 1 year(s) ago
txgemma-9b-chat
google/txgemma-9b-chat
arxiv:2504.06196
arxiv:2406.06316
Transformers
safetensors
endpoints_compatible
Text Generation
text-generation-inference
conversational
en
autotrain_compatible
gemma2
region:us
license:other
therapeutics
drug-development
- 0
- 6
- 0
- 184
Updated 1 year(s) ago
txgemma-9b-predict
google/txgemma-9b-predict
therapeutics
arxiv:2406.06316
arxiv:2504.06196
drug-development
license:other
region:us
gemma2
autotrain_compatible
en
text-generation-inference
Text Generation
endpoints_compatible
safetensors
Transformers
- 0
- 3
- 0
- 218
Updated 1 year(s) ago
medgemma-27b-text-it
google/medgemma-27b-text-it
arxiv:2303.15343
arxiv:2102.09542
arxiv:2009.13081
arxiv:2404.05590
base_model:google/gemma-3-27b-pt
arxiv:2501.18362
arxiv:2411.15640
arxiv:2501.19393
endpoints_compatible
Text Generation
text-generation-inference
conversational
safetensors
autotrain_compatible
medical
region:us
license:other
Transformers
gemma3_text
clinical-reasoning
thinking
base_model:finetune:google/gemma-3-27b-pt
- 0
- 5
- 0
- 863
Updated 1 year(s) ago
© 2026 - Copyright AIKosh. All rights reserved.