---
base_model: google/medgemma-27b-it
extra_gated_button_content: Acknowledge license
extra_gated_heading: Access MedGemma on Hugging Face
extra_gated_prompt: To access MedGemma on Hugging Face, you're required to review
  and agree to [Health AI Developer Foundation's terms of use](https://developers.google.com/health-ai-developer-foundations/terms).
  To do this, please ensure you're logged in to Hugging Face and click below. Requests
  are processed immediately.
language: en
library_name: transformers
license: other
license_link: https://developers.google.com/health-ai-developer-foundations/terms
license_name: health-ai-developer-foundations
mradermacher:
  readme_rev: 1
quantized_by: mradermacher
tags:
- medical
- x-ray
- pathology
- dermatology
- fundus
- radiology report generation
- chest-x-ray
- medical-embeddings
- image-classification
- zero-shot-image-classification
- image-feature-extraction
- image-text-to-text
---
## About

<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type:  -->
<!-- ### tags:  -->
static quants of https://huggingface.co/google/medgemma-27b-it

<!-- provided-files -->

***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#medgemma-27b-it-GGUF).***

weighted/imatrix quants are available at https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF
## Usage

If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.

## Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-GGUF/resolve/main/medgemma-27b-it.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.7 | multi-modal supplement |
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-GGUF/resolve/main/medgemma-27b-it.mmproj-f16.gguf) | mmproj-f16 | 1.0 | multi-modal supplement |
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-GGUF/resolve/main/medgemma-27b-it.Q2_K.gguf) | Q2_K | 10.6 |  |
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-GGUF/resolve/main/medgemma-27b-it.Q3_K_S.gguf) | Q3_K_S | 12.3 |  |
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-GGUF/resolve/main/medgemma-27b-it.Q3_K_M.gguf) | Q3_K_M | 13.5 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-GGUF/resolve/main/medgemma-27b-it.Q3_K_L.gguf) | Q3_K_L | 14.6 |  |
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-GGUF/resolve/main/medgemma-27b-it.IQ4_XS.gguf) | IQ4_XS | 15.0 |  |
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-GGUF/resolve/main/medgemma-27b-it.Q4_K_S.gguf) | Q4_K_S | 15.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-GGUF/resolve/main/medgemma-27b-it.Q4_K_M.gguf) | Q4_K_M | 16.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-GGUF/resolve/main/medgemma-27b-it.Q5_K_S.gguf) | Q5_K_S | 18.9 |  |
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-GGUF/resolve/main/medgemma-27b-it.Q5_K_M.gguf) | Q5_K_M | 19.4 |  |
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-GGUF/resolve/main/medgemma-27b-it.Q6_K.gguf) | Q6_K | 22.3 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-GGUF/resolve/main/medgemma-27b-it.Q8_0.gguf) | Q8_0 | 28.8 | fast, best quality |

Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):

![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)

And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

## FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.

## Thanks

I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.

<!-- end -->