Aller au contenu
ModelVérifiéExterne
Télécharger

Gemma 4 E4B It SOMPOA Heresy I1 GGUF

For a convenient overview and download list, visit our model page for this model.

Sourcehuggingface.co/mradermacher/gemma-4-E4B-it-SOMPOA-heresy-i1-GGUF/tree/aa572899be777793131f0072362db1a6ec59c295
TypeOtherModèle de baseMuXodious/gemma-4-E4B-it-SOMPOA-heresyVersionRevision aa57289Éditeur@mradermacherCClasse

Source du modèle

Type
Other
Taille du fichier
4,22 MB–5,75 GB
Modèle de base
MuXodious/gemma-4-E4B-it-SOMPOA-heresy
Version
vRevision aa57289
Mis à jour
22 oct. 2026
Éditeur
@mradermacher
Téléchargements
725
Source
Hugging Face

Description de la source

About

weighted/imatrix quants of https://huggingface.co/MuXodious/gemma-4-E4B-it-SOMPOA-heresy

For a convenient overview and download list, visit our model page for this model.

static quants are available at https://huggingface.co/mradermacher/gemma-4-E4B-it-SOMPOA-heresy-GGUF

This is a vision model - mmproj files (if any) will be in the static repository.

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs 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)

LinkTypeSize/GBNotes
GGUFimatrix0.1imatrix file (for creating your own quants)
GGUFi1-IQ1_S3.4for the desperate
GGUFi1-IQ1_M3.5mostly desperate
GGUFi1-IQ2_XXS3.6
GGUFi1-IQ2_XS3.7
GGUFi1-IQ2_S3.8
GGUFi1-IQ2_M3.9
GGUFi1-IQ3_XXS4.1lower quality
GGUFi1-Q2_K_S4.4very low quality
GGUFi1-Q2_K4.5IQ3_XXS probably better
GGUFi1-IQ3_XS4.6
GGUFi1-Q3_K_S4.7IQ3_XS probably better
GGUFi1-IQ3_S4.7beats Q3_K*
GGUFi1-IQ3_M4.8
GGUFi1-Q3_K_M4.9IQ3_S probably better
GGUFi1-Q3_K_L5.1IQ3_M probably better
GGUFi1-IQ4_XS5.1
GGUFi1-IQ4_NL5.3prefer IQ4_XS
GGUFi1-Q4_05.3fast, low quality
GGUFi1-Q4_K_S5.3optimal size/speed/quality
GGUFi1-Q4_K_M5.4fast, recommended
GGUFi1-Q4_15.5
GGUFi1-Q5_K_S5.7
GGUFi1-Q5_K_M5.8
GGUFi1-Q6_K6.3practically like static Q6_K

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

image.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, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to @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.

Sources

1 source
Hugging FacePrincipalVersion aa572899be777793131f0072362db1a6ec59c295
huggingface.co/mradermacher/gemma-4-E4B-it-SOMPOA-heresy-i1-GGUF/tree/aa572899be777793131f0072362db1a6ec59c295

Vérifié 22 oct.

Artefacts du modèle

25 artefacts

gemma-4-E4B-it-SOMPOA-heresy.i1-IQ1_M.gguf

gguf · 3,14 GB · SHA-256 fc1346b9ce2e…0732 · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-IQ1_S.gguf

gguf · 3,06 GB · SHA-256 3aa5de720e56…0bc5 · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-IQ2_M.gguf

gguf · 3,53 GB · SHA-256 66e441e03e2b…544f · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-IQ2_S.gguf

gguf · 3,42 GB · SHA-256 8e0a90bbc2db…140d · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-IQ2_XS.gguf

gguf · 3,38 GB · SHA-256 d70081a6c694…dd3f · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-IQ2_XXS.gguf

gguf · 3,27 GB · SHA-256 7a411dfd8719…3856 · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-IQ3_M.gguf

gguf · 4,37 GB · SHA-256 ea0603d93e7d…22fd · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-IQ3_S.gguf

gguf · 4,32 GB · SHA-256 ed2ea273311a…1d14 · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-IQ3_XS.gguf

gguf · 4,23 GB · SHA-256 d409c0a7c01f…d4a8 · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-IQ3_XXS.gguf

gguf · 3,71 GB · SHA-256 d3748de56869…45bb · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-IQ4_NL.gguf

gguf · 4,81 GB · SHA-256 d8f188b6ab46…b4d4 · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-IQ4_XS.gguf

gguf · 4,69 GB · SHA-256 b97ff25c8f2b…a70e · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-Q2_K_S.gguf

gguf · 3,98 GB · SHA-256 e69bd392a05a…db73 · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-Q2_K.gguf

gguf · 4,08 GB · SHA-256 168a5e52951b…1979 · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-Q3_K_L.gguf

gguf · 4,65 GB · SHA-256 2249dbc90ed2…caa5 · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-Q3_K_M.gguf

gguf · 4,49 GB · SHA-256 1ffc2a043923…8657 · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-Q3_K_S.gguf

gguf · 4,31 GB · SHA-256 b463b6594696…942d · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-Q4_0.gguf

gguf · 4,81 GB · SHA-256 92ab89f31f89…f774 · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-Q4_1.gguf

gguf · 5,03 GB · SHA-256 b8d7f510f707…e78c · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-Q4_K_M.gguf

gguf · 4,94 GB · SHA-256 f8e0c3f38ccf…fc95 · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-Q4_K_S.gguf

gguf · 4,82 GB · SHA-256 aa7ef7ad194b…8051 · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-Q5_K_M.gguf

gguf · 5,33 GB · SHA-256 203b21af92fa…806d · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-Q5_K_S.gguf

gguf · 5,26 GB · SHA-256 5c367d9f3f8f…49d0 · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.i1-Q6_K.gguf

gguf · 5,75 GB · SHA-256 bfb328eade18…5b1b · Hugging Face

Télécharger

gemma-4-E4B-it-SOMPOA-heresy.imatrix.gguf

gguf · 4,22 MB · SHA-256 85029f6ea522…6b36 · Hugging Face

Télécharger

Extraits de sources

3 extraits
Readme11 juil.huggingface.co/mradermacher/gemma-4-E4B-it-SOMPOA-heresy-i1-GGUF

--- base_model: MuXodious/gemma-4-E4B-it-SOMPOA-heresy language: - en library_name: transformers license: apache-2.0 license_link: https://ai.google.dev/gemma/docs/gemma_4_license mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - heretic - uncensored - decensored - abliterated --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> <!-- ### quants: Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S --> <!-- ### quants_skip: --> <!-- ### skip_mmproj: --> weighted/imatrix quants of https://huggingface.co/MuXodious/gemma-4-E4B-it-SOMPOA-heresy <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gemma-4-E4B-it-SOMPOA-heresy-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/gemma-4-E4B-it-SOMPOA-heresy-GGUF **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/gemma-4-E4B-it-SOMPOA-heresy-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-E4B-it-SOMPOA-heresy-i1-GGUF/resolve/main/gemma-4-E4B-it-SOMPOA-heresy.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/gemma-4-E4B-it-SOMPOA-heresy-i1-GGUF/resolve/main/gemma-4-E4B-it-SOMPOA-heresy.i1-IQ1_S.gguf) | i1-IQ1_S | 3.4 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/gemma-4-E4B-it-SOMPOA-heresy-i1-GGUF/resolve/main/gemma-4-E4B-it-SOMPOA-heresy.i1-IQ1_M.gguf) | i1-IQ1_M | 3.5 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/gemma-4-E4B-it-SOMPOA-heresy-i1-GGUF/resolve/main/gemma-4-E4B-it-SOMPOA-heresy.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.6 | | | [GGUF](https://huggingface.co/mrad...

Note22 oct.huggingface.co/mradermacher/gemma-4-E4B-it-SOMPOA-heresy-i1-GGUF

Source context: 725 downloads · 1 likes · Library transformers · Repo mradermacher/gemma-4-E4B-it-SOMPOA-heresy-i1-GGUF

Note6 aoûthuggingface.co/mradermacher/gemma-4-E4B-it-SOMPOA-heresy-i1-GGUF

Source context: 364 downloads · 1 likes · Library transformers · Repo mradermacher/gemma-4-E4B-it-SOMPOA-heresy-i1-GGUF