Aller au contenu
ModelVérifiéExterne
Télécharger

Gemma 4 12B It Uncensored Heretic I1 GGUF

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

Sourcehuggingface.co/mradermacher/gemma-4-12B-it-uncensored-heretic-i1-GGUF/tree/df44f9abd40c2567863261ebe50e4d1a0cb652e9
TypeOtherModèle de basellmfan46/gemma-4-12B-it-uncensored-hereticVersionRevision df44f9aÉditeur@mradermacherCClasse

Source du modèle

Type
Other
Taille du fichier
7,13 MB–9,11 GB
Modèle de base
llmfan46/gemma-4-12B-it-uncensored-heretic
Version
vRevision df44f9a
Mis à jour
3 oct. 2026
Éditeur
@mradermacher
Téléchargements
2,2 k
Paramètres
12B
Source
Hugging Face

Description de la source

About

weighted/imatrix quants of https://huggingface.co/llmfan46/gemma-4-12B-it-uncensored-heretic

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

static quants are available at https://huggingface.co/mradermacher/gemma-4-12B-it-uncensored-heretic-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_S3.1for the desperate
GGUFi1-IQ1_M3.3mostly desperate
GGUFi1-IQ2_XXS3.7
GGUFi1-IQ2_XS4.0
GGUFi1-IQ2_S4.2
GGUFi1-IQ2_M4.5
GGUFi1-Q2_K_S4.6very low quality
GGUFi1-Q2_K4.9IQ3_XXS probably better
GGUFi1-IQ3_XXS4.9lower quality
GGUFi1-IQ3_XS5.4
GGUFi1-IQ3_S5.6beats Q3_K*
GGUFi1-Q3_K_S5.6IQ3_XS probably better
GGUFi1-IQ3_M5.8
GGUFi1-Q3_K_M6.2IQ3_S probably better
GGUFi1-Q3_K_L6.7IQ3_M probably better
GGUFi1-IQ4_XS6.7
GGUFi1-IQ4_NL7.1prefer IQ4_XS
GGUFi1-Q4_07.1fast, low quality
GGUFi1-Q4_K_S7.1optimal size/speed/quality
GGUFi1-Q4_K_M7.5fast, recommended
GGUFi1-Q4_17.8
GGUFi1-Q5_K_S8.4
GGUFi1-Q5_K_M8.6
GGUFi1-Q6_K9.9practically 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 df44f9abd40c2567863261ebe50e4d1a0cb652e9
huggingface.co/mradermacher/gemma-4-12B-it-uncensored-heretic-i1-GGUF/tree/df44f9abd40c2567863261ebe50e4d1a0cb652e9

Vérifié 3 oct.

Artefacts du modèle

25 artefacts

gemma-4-12B-it-uncensored-heretic.i1-IQ1_M.gguf

gguf · 2,98 GB · SHA-256 0e4aa1df30bc…e665 · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-IQ1_S.gguf

gguf · 2,78 GB · SHA-256 8689fea5e9be…11db · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-IQ2_M.gguf

gguf · 4,07 GB · SHA-256 ef585accb645…96c6 · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-IQ2_S.gguf

gguf · 3,80 GB · SHA-256 6e5734601761…9aed · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-IQ2_XS.gguf

gguf · 3,62 GB · SHA-256 74ecc9696c0e…e1ca · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-IQ2_XXS.gguf

gguf · 3,32 GB · SHA-256 f8c00e5e8ba0…d625 · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-IQ3_M.gguf

gguf · 5,34 GB · SHA-256 b1010e2ed81e…015c · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-IQ3_S.gguf

gguf · 5,15 GB · SHA-256 1ab625ccee98…bd0f · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-IQ3_XS.gguf

gguf · 4,91 GB · SHA-256 3abeafb50379…0aba · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-IQ3_XXS.gguf

gguf · 4,52 GB · SHA-256 1275930465bf…5334 · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-IQ4_NL.gguf

gguf · 6,50 GB · SHA-256 5ddd61a9e70d…636b · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-IQ4_XS.gguf

gguf · 6,18 GB · SHA-256 1477a9a508f0…c0da · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-Q2_K_S.gguf

gguf · 4,19 GB · SHA-256 31efaef7d416…0483 · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-Q2_K.gguf

gguf · 4,50 GB · SHA-256 ecfcf908b7c3…a656 · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-Q3_K_L.gguf

gguf · 6,12 GB · SHA-256 428c017ce04a…cae5 · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-Q3_K_M.gguf

gguf · 5,67 GB · SHA-256 5b93d8f492ab…9a29 · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-Q3_K_S.gguf

gguf · 5,15 GB · SHA-256 ea88360a726d…189f · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-Q4_0.gguf

gguf · 6,52 GB · SHA-256 d45e5ef0b3be…01f6 · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-Q4_1.gguf

gguf · 7,13 GB · SHA-256 4e24d5f4cfa9…95c3 · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-Q4_K_M.gguf

gguf · 6,87 GB · SHA-256 c39fcb9b0a98…a68d · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-Q4_K_S.gguf

gguf · 6,54 GB · SHA-256 8ca1f5d7b42f…1ed1 · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-Q5_K_M.gguf

gguf · 7,96 GB · SHA-256 48de0d7766ef…3f0d · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-Q5_K_S.gguf

gguf · 7,77 GB · SHA-256 341917f66206…6c0b · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.i1-Q6_K.gguf

gguf · 9,11 GB · SHA-256 e0d526c71315…a3c2 · Hugging Face

Télécharger

gemma-4-12B-it-uncensored-heretic.imatrix.gguf

gguf · 7,13 MB · SHA-256 3c26f89d32cc…ca4c · Hugging Face

Télécharger

Extraits de sources

3 extraits
Readme11 juil.huggingface.co/mradermacher/gemma-4-12B-it-uncensored-heretic-i1-GGUF

--- base_model: llmfan46/gemma-4-12B-it-uncensored-heretic 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 - ara --- ## 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/llmfan46/gemma-4-12B-it-uncensored-heretic <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gemma-4-12B-it-uncensored-heretic-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/gemma-4-12B-it-uncensored-heretic-GGUF **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/gemma-4-12B-it-uncensored-heretic-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-4-12B-it-uncensored-heretic-i1-GGUF/resolve/main/gemma-4-12B-it-uncensored-heretic.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/gemma-4-12B-it-uncensored-heretic-i1-GGUF/resolve/main/gemma-4-12B-it-uncensored-heretic.i1-IQ1_S.gguf) | i1-IQ1_S | 3.1 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/gemma-4-12B-it-uncensored-heretic-i1-GGUF/resolve/main/gemma-4-12B-it-uncensored-heretic.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/gemma-4-12B-it-uncensored-heretic-i1-GGUF/resolve/main/gemma-4-12B-it-uncensored-heretic.i1-IQ2_...

Note3 oct.huggingface.co/mradermacher/gemma-4-12B-it-uncensored-heretic-i1-GGUF

Source context: 2248 downloads · 3 likes · Library transformers · Repo mradermacher/gemma-4-12B-it-uncensored-heretic-i1-GGUF

Note17 juil.huggingface.co/mradermacher/gemma-4-12B-it-uncensored-heretic-i1-GGUF

Source context: 2074 downloads · 3 likes · Library transformers · Repo mradermacher/gemma-4-12B-it-uncensored-heretic-i1-GGUF