You can deploy this model and start earning money today!

Mungert/
medgemma-27b-text-it-GGUF

Name: medgemma-27b-text-it-GGUF
Rating: 2.5 (175 reviews)

Views

No views yet

medgemma-27b-text-it GGUF Models

Model Generation Details

This model was generated using llama.cpp at commit f5cd27b7.

Ultra-Low-Bit Quantization with IQ-DynamicGate (1-2 bit)

Our latest quantization method introduces precision-adaptive quantization for ultra-low-bit models (1-2 bit), with benchmark-proven improvements on Llama-3-8B. This approach uses layer-specific strategies to preserve accuracy while maintaining extreme memory efficiency.

Benchmark Context

All tests conducted on Llama-3-8B-Instruct using:

Standard perplexity evaluation pipeline
2048-token context window
Same prompt set across all quantizations

Method

Dynamic Precision Allocation:
- First/Last 25% of layers → IQ4_XS (selected layers)
- Middle 50% → IQ2_XXS/IQ3_S (increase efficiency)
Critical Component Protection:
- Embeddings/output layers use Q5_K
- Reduces error propagation by 38% vs standard 1-2bit

Quantization Performance Comparison (Llama-3-8B)

Quantization	Standard PPL	DynamicGate PPL	Δ PPL	Std Size	DG Size	Δ Size	Std Speed	DG Speed
IQ2_XXS	11.30	9.84	-12.9%	2.5G	2.6G	+0.1G	234s	246s
IQ2_XS	11.72	11.63	-0.8%	2.7G	2.8G	+0.1G	242s	246s
IQ2_S	14.31	9.02	-36.9%	2.7G	2.9G	+0.2G	238s	244s
IQ1_M	27.46	15.41	-43.9%	2.2G	2.5G	+0.3G	206s	212s
IQ1_S	53.07	32.00	-39.7%	2.1G	2.4G	+0.3G	184s	209s

Key:

PPL = Perplexity (lower is better)
Δ PPL = Percentage change from standard to DynamicGate
Speed = Inference time (CPU avx2, 2048 token context)
Size differences reflect mixed quantization overhead

Key Improvements:

🔥 IQ1_M shows massive 43.9% perplexity reduction (27.46 → 15.41)
🚀 IQ2_S cuts perplexity by 36.9% while adding only 0.2GB
⚡ IQ1_S maintains 39.7% better accuracy despite 1-bit quantization

Tradeoffs:

All variants have modest size increases (0.1-0.3GB)
Inference speeds remain comparable (<5% difference)

When to Use These Models

📌 Fitting models into GPU VRAM

✔ Memory-constrained deployments

✔ Cpu and Edge Devices where 1-2bit errors can be tolerated

✔ Research into ultra-low-bit quantization

Choosing the Right Model Format

Selecting the correct model format depends on your hardware capabilities and memory constraints.

BF16 (Brain Float 16) – Use if BF16 acceleration is available

A 16-bit floating-point format designed for faster computation while retaining good precision.
Provides similar dynamic range as FP32 but with lower memory usage.
Recommended if your hardware supports BF16 acceleration (check your device's specs).
Ideal for high-performance inference with reduced memory footprint compared to FP32.

📌 Use BF16 if:
✔ Your hardware has native BF16 support (e.g., newer GPUs, TPUs).
✔ You want higher precision while saving memory.
✔ You plan to requantize the model into another format.

📌 Avoid BF16 if:
❌ Your hardware does not support BF16 (it may fall back to FP32 and run slower).
❌ You need compatibility with older devices that lack BF16 optimization.

F16 (Float 16) – More widely supported than BF16

A 16-bit floating-point high precision but with less of range of values than BF16.
Works on most devices with FP16 acceleration support (including many GPUs and some CPUs).
Slightly lower numerical precision than BF16 but generally sufficient for inference.

📌 Use F16 if:
✔ Your hardware supports FP16 but not BF16.
✔ You need a balance between speed, memory usage, and accuracy.
✔ You are running on a GPU or another device optimized for FP16 computations.

📌 Avoid F16 if:
❌ Your device lacks native FP16 support (it may run slower than expected).
❌ You have memory limitations.

Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference

Quantization reduces model size and memory usage while maintaining as much accuracy as possible.

Lower-bit models (Q4_K) → Best for minimal memory usage, may have lower precision.
Higher-bit models (Q6_K, Q8_0) → Better accuracy, requires more memory.

📌 Use Quantized Models if:
✔ You are running inference on a CPU and need an optimized model.
✔ Your device has low VRAM and cannot load full-precision models.
✔ You want to reduce memory footprint while keeping reasonable accuracy.

📌 Avoid Quantized Models if:
❌ You need maximum accuracy (full-precision models are better for this).
❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16).

Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0)

These models are optimized for extreme memory efficiency, making them ideal for low-power devices or large-scale deployments where memory is a critical constraint.

IQ3_XS: Ultra-low-bit quantization (3-bit) with extreme memory efficiency.
- Use case: Best for ultra-low-memory devices where even Q4_K is too large.
- Trade-off: Lower accuracy compared to higher-bit quantizations.
IQ3_S: Small block size for maximum memory efficiency.
- Use case: Best for low-memory devices where IQ3_XS is too aggressive.
IQ3_M: Medium block size for better accuracy than IQ3_S.
- Use case: Suitable for low-memory devices where IQ3_S is too limiting.
Q4_K: 4-bit quantization with block-wise optimization for better accuracy.
- Use case: Best for low-memory devices where Q6_K is too large.
Q4_0: Pure 4-bit quantization, optimized for ARM devices.
- Use case: Best for ARM-based devices or low-memory environments.

Summary Table: Model Format Selection

Model Format	Precision	Memory Usage	Device Requirements	Best Use Case
BF16	Highest	High	BF16-supported GPU/CPUs	High-speed inference with reduced memory
F16	High	High	FP16-supported devices	GPU inference when BF16 isn't available
Q4_K	Medium Low	Low	CPU or Low-VRAM devices	Best for memory-constrained environments
Q6_K	Medium	Moderate	CPU with more memory	Better accuracy while still being quantized
Q8_0	High	Moderate	CPU or GPU with enough VRAM	Best accuracy among quantized models
IQ3_XS	Very Low	Very Low	Ultra-low-memory devices	Extreme memory efficiency and low accuracy
Q4_0	Low	Low	ARM or low-memory devices	llama.cpp can optimize for ARM devices

Included Files & Details

`medgemma-27b-text-it-bf16.gguf`

Model weights preserved in BF16.
Use this if you want to requantize the model into a different format.
Best if your device supports BF16 acceleration.

`medgemma-27b-text-it-f16.gguf`

Model weights stored in F16.
Use if your device supports FP16, especially if BF16 is not available.

`medgemma-27b-text-it-bf16-q8_0.gguf`

Output & embeddings remain in BF16.
All other layers quantized to Q8_0.
Use if your device supports BF16 and you want a quantized version.

`medgemma-27b-text-it-f16-q8_0.gguf`

Output & embeddings remain in F16.
All other layers quantized to Q8_0.

`medgemma-27b-text-it-q4_k.gguf`

Output & embeddings quantized to Q8_0.
All other layers quantized to Q4_K.
Good for CPU inference with limited memory.

`medgemma-27b-text-it-q4_k_s.gguf`

Smallest Q4_K variant, using less memory at the cost of accuracy.
Best for very low-memory setups.

`medgemma-27b-text-it-q6_k.gguf`

Output & embeddings quantized to Q8_0.
All other layers quantized to Q6_K .

`medgemma-27b-text-it-q8_0.gguf`

Fully Q8 quantized model for better accuracy.
Requires more memory but offers higher precision.

`medgemma-27b-text-it-iq3_xs.gguf`

IQ3_XS quantization, optimized for extreme memory efficiency.
Best for ultra-low-memory devices.

`medgemma-27b-text-it-iq3_m.gguf`

IQ3_M quantization, offering a medium block size for better accuracy.
Suitable for low-memory devices.

`medgemma-27b-text-it-q4_0.gguf`

Pure Q4_0 quantization, optimized for ARM devices.
Best for low-memory environments.
Prefer IQ4_NL for better accuracy.

🚀 If you find these models useful

❤ Please click "Like" if you find this useful!
Help me test my AI-Powered Network Monitor Assistant with quantum-ready security checks:
👉 Quantum Network Monitor

💬 How to test:
Choose an AI assistant type:

TurboLLM (GPT-4o-mini)
HugLLM (Hugginface Open-source)
TestLLM (Experimental CPU-only)

What I’m Testing

I’m pushing the limits of small open-source models for AI network monitoring, specifically:

Function calling against live network services
How small can a model go while still handling:
- Automated Nmap scans
- Quantum-readiness checks
- Network Monitoring tasks

🟡 TestLLM – Current experimental model (llama.cpp on 2 CPU threads):

✅ Zero-configuration setup
⏳ 30s load time (slow inference but no API costs)
🔧 Help wanted! If you’re into edge-device AI, let’s collaborate!

Other Assistants

🟢 TurboLLM – Uses gpt-4o-mini for:

Create custom cmd processors to run .net code on Quantum Network Monitor Agents
Real-time network diagnostics and monitoring
Security Audits
Penetration testing (Nmap/Metasploit)

🔵 HugLLM – Latest Open-source models:

🌐 Runs on Hugging Face Inference API

💡 Example commands to you could test:

"Give me info on my websites SSL certificate"
"Check if my server is using quantum safe encyption for communication"
"Run a comprehensive security audit on my server"
'"Create a cmd processor to .. (what ever you want)" Note you need to install a Quantum Network Monitor Agent to run the .net code from. This is a very flexible and powerful feature. Use with caution!

Final Word

I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is open source. Feel free to use whatever you find helpful.

If you appreciate the work, please consider buying me a coffee ☕. Your support helps cover service costs and allows me to raise token limits for everyone.

I'm also open to job opportunities or sponsorship.

Thank you! 😊

MedGemma model card

Model documentation: MedGemma

Resources:

Model on Google Cloud Model Garden: MedGemma
Model on Hugging Face: MedGemma
GitHub repository (supporting code, Colab notebooks, discussions, and issues): MedGemma
Quick start notebook: GitHub
Fine-tuning notebook: GitHub
Patient Education Demo built using MedGemma
Support: See Contact
License: The use of MedGemma is governed by the Health AI Developer Foundations terms of use.

Author: Google

Model information

This section describes the MedGemma model and how to use it.

Description

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.

How to use

Below are some example code snippets to help you quickly get started running the model locally on GPU. If you want to use the model at scale, we recommend that you create a production version using Model Garden.

First, install the Transformers library. Gemma 3 is supported starting from transformers 4.50.0.

$ pip install -U transformers

Run model with the pipeline API

python

from transformers import pipeline
import torch

pipe = pipeline(
    "text-generation",
    model="google/medgemma-27b-text-it",
    torch_dtype=torch.bfloat16,
    device="cuda",
)

messages = [
    {
        "role": "system",
        "content": "You are a helpful medical assistant."
    },
    {
        "role": "user",
        "content": "How do you differentiate bacterial from viral pneumonia?"
    }
]

output = pipe(text=messages, max_new_tokens=200)
print(output[0]["generated_text"][-1]["content"])

Run the model directly

python

# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "google/medgemma-27b-text-it"

model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

messages = [
    {
        "role": "system",
        "content": "You are a helpful medical assistant."
    },
    {
        "role": "user",
        "content": "How do you differentiate bacterial from viral pneumonia?"
    }
]

inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device)

input_len = inputs["input_ids"].shape[-1]

with torch.inference_mode():
    generation = model.generate(**inputs, max_new_tokens=200, do_sample=False)
    generation = generation[0][input_len:]

decoded = tokenizer.decode(generation, skip_special_tokens=True)
print(decoded)

Examples

See the following Colab notebooks for examples of how to use MedGemma:

To give the model a quick try, running it locally with weights from Hugging Face, see Quick start notebook in Colab. Note that you will need to use Colab Enterprise to run the 27B model without quantization.
For an example of fine-tuning the model, see the Fine-tuning notebook in Colab.

Model architecture overview

The MedGemma model is built based on Gemma 3 and uses the same decoder-only transformer architecture as Gemma 3. To read more about the architecture, consult the Gemma 3 model card.

Technical specifications

Model type: Decoder-only Transformer architecture, see the Gemma 3 technical report
Modalities: 4B: Text, vision; 27B: Text only
Attention mechanism: Utilizes grouped-query attention (GQA)
Context length: Supports long context, at least 128K tokens
Key publication: Coming soon
Model created: May 20, 2025
Model version: 1.0.0

Citation

A technical report is coming soon. In the meantime, if you publish using this model, please cite the Hugging Face model page:

none

@misc{medgemma-hf,
    author = {Google},
    title = {MedGemma Hugging Face}
    howpublished = {\url{https://huggingface.co/collections/google/medgemma-release-680aade845f90bec6a3f60c4}},
    year = {2025},
    note = {Accessed: [Insert Date Accessed, e.g., 2025-05-20]}
}

Inputs and outputs

Input:

Text string, such as a question or prompt
Total input length of 128K tokens

Output:

Generated text in response to the input, such as an answer to a question, analysis of image content, or a summary of a document
Total output length of 8192 tokens

Performance and validation

MedGemma was evaluated across a range of different multimodal classification, report generation, visual question answering, and text-based tasks.

Key performance metrics

Text evaluations

MedGemma 4B and text-only MedGemma 27B were evaluated across a range of text-only benchmarks for medical knowledge and reasoning.

The MedGemma models outperform their respective base Gemma models across all tested text-only health benchmarks.

Metric	MedGemma 27B	Gemma 3 27B	MedGemma 4B	Gemma 3 4B
MedQA (4-op)	89.8 (best-of-5) 87.7 (0-shot)	74.9	64.4	50.7
MedMCQA	74.2	62.6	55.7	45.4
PubMedQA	76.8	73.4	73.4	68.4
MMLU Med (text only)	87.0	83.3	70.0	67.2
MedXpertQA (text only)	26.7	15.7	14.2	11.6
AfriMed-QA	84.0	72.0	52.0	48.0

For all MedGemma 27B results, test-time scaling is used to improve performance.

Ethics and safety evaluation

Evaluation approach

Our evaluation methods include structured evaluations and internal red-teaming testing of relevant content policies. Red-teaming was conducted by a number of different teams, each with different goals and human evaluation metrics. These models were evaluated against a number of different categories relevant to ethics and safety, including:

Child safety: Evaluation of text-to-text and image-to-text prompts covering child safety policies, including child sexual abuse and exploitation.
Content safety: Evaluation of text-to-text and image-to-text prompts covering safety policies, including harassment, violence and gore, and hate speech.
Representational harms: Evaluation of text-to-text and image-to-text prompts covering safety policies, including bias, stereotyping, and harmful associations or inaccuracies.
General medical harms: Evaluation of text-to-text and image-to-text prompts covering safety policies, including information quality and harmful associations or inaccuracies.

In addition to development level evaluations, we conduct "assurance evaluations" which are our "arms-length" internal evaluations for responsibility governance decision making. They are conducted separately from the model development team, to inform decision making about release. High-level findings are fed back to the model team, but prompt sets are held out to prevent overfitting and preserve the results' ability to inform decision making. Notable assurance evaluation results are reported to our Responsibility & Safety Council as part of release review.

Evaluation results

For all areas of safety testing, we saw safe levels of performance across the categories of child safety, content safety, and representational harms. All testing was conducted without safety filters to evaluate the model capabilities and behaviors. For text-to-text, image-to-text, and audio-to-text, and across both MedGemma model sizes, the model produced minimal policy violations. A limitation of our evaluations was that they included primarily English language prompts.

Data card

Dataset overview

Training

The base Gemma models are pre-trained on a large corpus of text and code data. MedGemma 4B utilizes a SigLIP image encoder that has been specifically pre-trained on a variety of de-identified medical data, including radiology images, histopathology images, ophthalmology images, and dermatology images. Its LLM component is trained on a diverse set of medical data, including medical text relevant to radiology images, chest-x rays, histopathology patches, ophthalmology images and dermatology images.

Evaluation

MedGemma models have been evaluated on a comprehensive set of clinically relevant benchmarks, including over 22 datasets across 5 different tasks and 6 medical image modalities. These include both open benchmark datasets and curated datasets, with a focus on expert human evaluations for tasks like CXR report generation and radiology VQA.

Source

MedGemma utilizes a combination of public and private datasets.

This model was trained on diverse public datasets including MIMIC-CXR (chest X-rays and reports), Slake-VQA (multimodal medical images and questions), PAD-UFES-20 (skin lesion images and data), SCIN (dermatology images), TCGA (cancer genomics data), CAMELYON (lymph node histopathology images), PMC-OA (biomedical literature with images), and Mendeley Digital Knee X-Ray (knee X-rays).

Additionally, multiple diverse proprietary datasets were licensed and incorporated (described next).

Data Ownership and Documentation

Mimic-CXR: MIT Laboratory for Computational Physiology and Beth Israel Deaconess Medical Center (BIDMC).
Slake-VQA: The Hong Kong Polytechnic University (PolyU), with collaborators including West China Hospital of Sichuan University and Sichuan Academy of Medical Sciences / Sichuan Provincial People's Hospital.
PAD-UFES-20: Federal University of Espírito Santo (UFES), Brazil, through its Dermatological and Surgical Assistance Program (PAD).
SCIN: A collaboration between Google Health and Stanford Medicine.
TCGA (The Cancer Genome Atlas): A joint effort of National Cancer Institute and National Human Genome Research Institute. Data from TCGA are available via the Genomic Data Commons (GDC)
CAMELYON: The data was collected from Radboud University Medical Center and University Medical Center Utrecht in the Netherlands.
PMC-OA (PubMed Central Open Access Subset): Maintained by the National Library of Medicine (NLM) and National Center for Biotechnology Information (NCBI), which are part of the NIH.
MedQA: This dataset was created by a team of researchers led by Di Jin, Eileen Pan, Nassim Oufattole, Wei-Hung Weng, Hanyi Fang, and Peter Szolovits
Mendeley Digital Knee X-Ray: This dataset is from Rani Channamma University, and is hosted on Mendeley Data.
AfriMed-QA: This data was developed and led by multiple collaborating organizations and researchers include key contributors: Intron Health, SisonkeBiotik, BioRAMP, Georgia Institute of Technology, and MasakhaneNLP.
VQA-RAD: This dataset was created by a research team led by Jason J. Lau, Soumya Gayen, Asma Ben Abacha, and Dina Demner-Fushman and their affiliated institutions (the US National Library of Medicine and National Institutes of Health)
MedExpQA: This dataset was created by researchers at the HiTZ Center (Basque Center for Language Technology and Artificial Intelligence).
MedXpertQA: This dataset was developed by researchers at Tsinghua University (Beijing, China) and Shanghai Artificial Intelligence Laboratory (Shanghai, China).

In addition to the public datasets listed above, MedGemma was also trained on de-identified datasets licensed for research or collected internally at Google from consented participants.

Radiology dataset 1: De-identified dataset of different CT studies across body parts from a US-based radiology outpatient diagnostic center network.
Ophthalmology dataset 1: De-identified dataset of fundus images from diabetic retinopathy screening.
Dermatology dataset 1: De-identified dataset of teledermatology skin condition images (both clinical and dermatoscopic) from Colombia.
Dermatology dataset 2: De-identified dataset of skin cancer images (both clinical and dermatoscopic) from Australia.
Dermatology dataset 3: De-identified dataset of non-diseased skin images from an internal data collection effort.
Pathology dataset 1: De-identified dataset of histopathology H&E whole slide images created in collaboration with an academic research hospital and biobank in Europe. Comprises de-identified colon, prostate, and lymph nodes.
Pathology dataset 2: De-identified dataset of lung histopathology H&E and IHC whole slide images created by a commercial biobank in the United States.
Pathology dataset 3: De-identified dataset of prostate and lymph node H&E and IHC histopathology whole slide images created by a contract research organization in the United States.
Pathology dataset 4: De-identified dataset of histopathology, predominantly H&E whole slide images created in collaboration with a large, tertiary teaching hospital in the United States. Comprises a diverse set of tissue and stain types, predominantly H&E.

Data citation

MIMIC-CXR Johnson, A., Pollard, T., Mark, R., Berkowitz, S., & Horng, S. (2024). MIMIC-CXR Database (version 2.1.0). PhysioNet. https://physionet.org/content/mimic-cxr/2.1.0/ and Johnson, Alistair E. W., Tom J. Pollard, Seth J. Berkowitz, Nathaniel R. Greenbaum, Matthew P. Lungren, Chih-Ying Deng, Roger G. Mark, and Steven Horng. 2019. "MIMIC-CXR, a de-Identified Publicly Available Database of Chest Radiographs with Free-Text Reports." Scientific Data 6 (1): 1–8.
SLAKE Liu, Bo, Li-Ming Zhan, Li Xu, Lin Ma, Yan Yang, and Xiao-Ming Wu. 2021.SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering." http://arxiv.org/abs/2102.09542.
PAD-UEFS Pacheco, A. G. C., Lima, G. R., Salomao, A., Krohling, B., Biral, I. P., de Angelo, G. G., Alves, F. O. G., Ju X. M., & P. R. C. (2020). PAD-UFES-20: A skin lesion dataset composed of patient data and clinical images collected from smartphones. In Proceedings of the 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 1551-1558). IEEE. https://doi.org/10.1109/BIBM49941.2020.9313241
SCIN Ward, Abbi, Jimmy Li, Julie Wang, Sriram Lakshminarasimhan, Ashley Carrick, Bilson Campana, Jay Hartford, et al. 2024. "Creating an Empirical Dermatology Dataset Through Crowdsourcing With Web Search Advertisements." JAMA Network Open 7 (11): e2446615–e2446615.
TCGA The results shown here are in whole or part based upon data generated by the TCGA Research Network: https://www.cancer.gov/tcga.
CAMELYON16 Ehteshami Bejnordi, Babak, Mitko Veta, Paul Johannes van Diest, Bram van Ginneken, Nico Karssemeijer, Geert Litjens, Jeroen A. W. M. van der Laak, et al. 2017. "Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer." JAMA 318 (22): 2199–2210.
MedQA Jin, Di, Eileen Pan, Nassim Oufattole, Wei-Hung Weng, Hanyi Fang, and Peter Szolovits. 2020. "What Disease Does This Patient Have? A Large-Scale Open Domain Question Answering Dataset from Medical Exams." http://arxiv.org/abs/2009.13081.
Mendeley Digital Knee X-Ray Gornale, Shivanand; Patravali, Pooja (2020), "Digital Knee X-ray Images", Mendeley Data, V1, doi: 10.17632/t9ndx37v5h.1
AfrimedQA Olatunji, Tobi, Charles Nimo, Abraham Owodunni, Tassallah Abdullahi, Emmanuel Ayodele, Mardhiyah Sanni, Chinemelu Aka, et al. 2024. "AfriMed-QA: A Pan-African, Multi-Specialty, Medical Question-Answering Benchmark Dataset." http://arxiv.org/abs/2411.15640.
VQA-RAD Lau, Jason J., Soumya Gayen, Asma Ben Abacha, and Dina Demner-Fushman. 2018. "A Dataset of Clinically Generated Visual Questions and Answers about Radiology Images." Scientific Data 5 (1): 1–10.
MedexpQA Alonso, I., Oronoz, M., & Agerri, R. (2024). MedExpQA: Multilingual Benchmarking of Large Language Models for Medical Question Answering. arXiv preprint arXiv:2404.05590. Retrieved from https://arxiv.org/abs/2404.05590
MedXpertQA Zuo, Yuxin, Shang Qu, Yifei Li, Zhangren Chen, Xuekai Zhu, Ermo Hua, Kaiyan Zhang, Ning Ding, and Bowen Zhou. 2025. "MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding." http://arxiv.org/abs/2501.18362.

De-identification/anonymization:

Google and partnerships utilize datasets that have been rigorously anonymized or de-identified to ensure the protection of individual research participants and patient privacy

Implementation information

Details about the model internals.

Software

Training was done using JAX.

JAX allows researchers to take advantage of the latest generation of hardware, including TPUs, for faster and more efficient training of large models.

Use and limitations

Intended use

MedGemma is an open multimodal generative AI model intended to be used as a starting point that enables more efficient development of downstream healthcare applications involving medical text and images. MedGemma is intended for developers in the life sciences and healthcare space. Developers are responsible for training, adapting and making meaningful changes to MedGemma to accomplish their specific intended use. MedGemma models can be fine-tuned by developers using their own proprietary data for their specific tasks or solutions.

MedGemma is based on Gemma 3 and has been further trained on medical images and text. MedGemma enables further development in any medical context (image and textual), however the model was pre-trained using chest X-ray, pathology, dermatology, and fundus images. Examples of tasks within MedGemma's training include visual question answering pertaining to medical images, such as radiographs, or providing answers to textual medical questions. Full details of all the tasks MedGemma has been evaluated can be found in an upcoming technical report.

Benefits

Provides strong baseline medical image and text comprehension for models of its size.
This strong performance makes it efficient to adapt for downstream healthcare-based use cases, compared to models of similar size without medical data pre-training.
This adaptation may involve prompt engineering, grounding, agentic orchestration or fine-tuning depending on the use case, baseline validation requirements, and desired performance characteristics.

Limitations

MedGemma is not intended to be used without appropriate validation, adaptation and/or making meaningful modification by developers for their specific use case. The outputs generated by MedGemma are not intended to directly inform clinical diagnosis, patient management decisions, treatment recommendations, or any other direct clinical practice applications. Performance benchmarks highlight baseline capabilities on relevant benchmarks, but even for image and text domains that constitute a substantial portion of training data, inaccurate model output is possible. All outputs from MedGemma should be considered preliminary and require independent verification, clinical correlation, and further investigation through established research and development methodologies.

MedGemma's multimodal capabilities have been primarily evaluated on single-image tasks. MedGemma has not been evaluated in use cases that involve comprehension of multiple images.

MedGemma has not been evaluated or optimized for multi-turn applications.

MedGemma's training may make it more sensitive to the specific prompt used than Gemma 3.

When adapting MedGemma developer should consider the following:

Bias in validation data: As with any research, developers should ensure that any downstream application is validated to understand performance using data that is appropriately representative of the intended use setting for the specific application (e.g., age, sex, gender, condition, imaging device, etc).
Data contamination concerns: When evaluating the generalization capabilities of a large model like MedGemma in a medical context, there is a risk of data contamination, where the model might have inadvertently seen related medical information during its pre-training, potentially overestimating its true ability to generalize to novel medical concepts. Developers should validate MedGemma on datasets not publicly available or otherwise made available to non-institutional researchers to mitigate this risk.

Mungert/medgemma-27b-text-it-GGUF