---
base_model: ValiantLabs/gemma-4-31B-it-Guardpoint
datasets:
- sequelbox/Superpotion-DeepSeek-V3.2-Speciale
language:
- en
library_name: transformers
license: apache-2.0
mradermacher:
  readme_rev: 1
quantized_by: mradermacher
tags:
- guardpoint
- valiant
- valiant-labs
- gemma
- gemma-4
- gemma-4-31B-it
- reasoning
- science
- science-reasoning
- medicine
- internal-medicine
- clinical-diagnosis
- medical-understanding
- medical-reasoning
- medical-diagnosis
- medical-management
- problem-solving
- anatomy
- angiology
- bariatric
- cardiovascular
- dental
- dermatology
- endocrinology
- ENT
- hematology
- immunology
- infectious-disease
- musculoskeletal
- neurology
- obstetrics
- ophtamology
- oncology
- orthopedics
- pathology
- psychiatry
- pulmonology
- radiology
- surgery
- triage
- urology
- analytical
- data
- data-interpretation
- expert
- rationality
- conversational
- chat
- instruct
---
## About

<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type:  -->
<!-- ### tags:  -->
<!-- ### quants:  x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS -->
<!-- ### quants_skip:  -->
<!-- ### skip_mmproj:  -->
static quants of https://huggingface.co/ValiantLabs/gemma-4-31B-it-Guardpoint

<!-- provided-files -->

***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gemma-4-31B-it-Guardpoint-GGUF).***

weighted/imatrix quants are available at https://huggingface.co/mradermacher/gemma-4-31B-it-Guardpoint-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/gemma-4-31B-it-Guardpoint-GGUF/resolve/main/gemma-4-31B-it-Guardpoint.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement |
| [GGUF](https://huggingface.co/mradermacher/gemma-4-31B-it-Guardpoint-GGUF/resolve/main/gemma-4-31B-it-Guardpoint.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement |
| [GGUF](https://huggingface.co/mradermacher/gemma-4-31B-it-Guardpoint-GGUF/resolve/main/gemma-4-31B-it-Guardpoint.Q2_K.gguf) | Q2_K | 12.0 |  |
| [GGUF](https://huggingface.co/mradermacher/gemma-4-31B-it-Guardpoint-GGUF/resolve/main/gemma-4-31B-it-Guardpoint.Q3_K_S.gguf) | Q3_K_S | 13.9 |  |
| [GGUF](https://huggingface.co/mradermacher/gemma-4-31B-it-Guardpoint-GGUF/resolve/main/gemma-4-31B-it-Guardpoint.Q3_K_M.gguf) | Q3_K_M | 15.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/gemma-4-31B-it-Guardpoint-GGUF/resolve/main/gemma-4-31B-it-Guardpoint.Q3_K_L.gguf) | Q3_K_L | 16.7 |  |
| [GGUF](https://huggingface.co/mradermacher/gemma-4-31B-it-Guardpoint-GGUF/resolve/main/gemma-4-31B-it-Guardpoint.IQ4_XS.gguf) | IQ4_XS | 17.0 |  |
| [GGUF](https://huggingface.co/mradermacher/gemma-4-31B-it-Guardpoint-GGUF/resolve/main/gemma-4-31B-it-Guardpoint.Q4_K_S.gguf) | Q4_K_S | 17.9 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/gemma-4-31B-it-Guardpoint-GGUF/resolve/main/gemma-4-31B-it-Guardpoint.Q4_K_M.gguf) | Q4_K_M | 18.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/gemma-4-31B-it-Guardpoint-GGUF/resolve/main/gemma-4-31B-it-Guardpoint.Q5_K_S.gguf) | Q5_K_S | 21.4 |  |
| [GGUF](https://huggingface.co/mradermacher/gemma-4-31B-it-Guardpoint-GGUF/resolve/main/gemma-4-31B-it-Guardpoint.Q5_K_M.gguf) | Q5_K_M | 21.9 |  |
| [GGUF](https://huggingface.co/mradermacher/gemma-4-31B-it-Guardpoint-GGUF/resolve/main/gemma-4-31B-it-Guardpoint.Q6_K.gguf) | Q6_K | 25.3 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/gemma-4-31B-it-Guardpoint-GGUF/resolve/main/gemma-4-31B-it-Guardpoint.Q8_0.gguf) | Q8_0 | 32.7 | 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.

<!-- end -->