Saltar al contenido
ModelVerificadoExterno
Descargar

Gemma 4 26B A4B It Qat Q4 0 Unquantized Heretic I1 GGUF

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

Fuentehuggingface.co/mradermacher/gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic-i1-GGUF/tree/3ef451e7d3d3f6661fbfba599673d5cc80821466
TipoOtherModelo basecoder3101/gemma-4-26B-A4B-it-qat-q4_0-unquantized-hereticVersiónRevision 3ef451ePublicador@mradermacherCcalidad

Fuente del modelo

Tipo
Other
Tamaño del archivo
54,3 MB–15,6 GB
Modelo base
coder3101/gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic
Versión
vRevision 3ef451e
Actualizado
3 oct 2026
Publicador
@mradermacher
Descargas
1,5 mil
Parámetros
26B
Fuente
Hugging Face

Descripción de la fuente

About

weighted/imatrix quants of https://huggingface.co/coder3101/gemma-4-26B-A4B-it-qat-q4_0-unquantized-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-4-26B-A4B-it-qat-q4_0-unquantized-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
GGUFimatrix0.2imatrix file (for creating your own quants)
GGUFi1-IQ1_S8.4for the desperate
GGUFi1-IQ1_M8.8mostly desperate
GGUFi1-IQ2_XXS9.4
GGUFi1-IQ2_XS9.9
GGUFi1-IQ2_S10.0
GGUFi1-IQ2_M10.5
GGUFi1-Q2_K10.7IQ3_XXS probably better
GGUFi1-Q2_K_S10.7very low quality
GGUFi1-IQ3_XXS11.4lower quality
GGUFi1-IQ3_XS11.7
GGUFi1-IQ3_S12.3beats Q3_K*
GGUFi1-Q3_K_S12.3IQ3_XS probably better
GGUFi1-IQ3_M12.5
GGUFi1-Q3_K_M13.4IQ3_S probably better
GGUFi1-Q3_K_L13.9IQ3_M probably better
GGUFi1-IQ4_XS14.0
GGUFi1-Q4_014.6fast, low quality
GGUFi1-Q4_K_S15.6optimal size/speed/quality
GGUFi1-Q4_116.1
GGUFi1-Q4_K_M16.9fast, recommended

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.

Fuentes

1 fuente
Hugging FacePrincipalVersión 3ef451e7d3d3f6661fbfba599673d5cc80821466
huggingface.co/mradermacher/gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic-i1-GGUF/tree/3ef451e7d3d3f6661fbfba599673d5cc80821466

Verificado 3 oct

Artefactos del modelo

21 artefactos

gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.i1-IQ1_M.gguf

gguf · 8,07 GB · SHA-256 aaf0f4998efa…be5f · Hugging Face

Descargar

gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.i1-IQ1_S.gguf

gguf · 7,72 GB · SHA-256 e4f515dc6527…57b3 · Hugging Face

Descargar

gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.i1-IQ2_M.gguf

gguf · 9,67 GB · SHA-256 22ad5162b6e2…ffc1 · Hugging Face

Descargar

gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.i1-IQ2_S.gguf

gguf · 9,20 GB · SHA-256 5ab6845efe2a…853e · Hugging Face

Descargar

gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.i1-IQ2_XS.gguf

gguf · 9,14 GB · SHA-256 2f52c4b963d7…bd94 · Hugging Face

Descargar

gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.i1-IQ2_XXS.gguf

gguf · 8,66 GB · SHA-256 149bd00a5715…3198 · Hugging Face

Descargar

gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.i1-IQ3_M.gguf

gguf · 11,5 GB · SHA-256 37dbf72e7f2b…7a2f · Hugging Face

Descargar

gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.i1-IQ3_S.gguf

gguf · 11,4 GB · SHA-256 c518c2e095a0…9886 · Hugging Face

Descargar

gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.i1-IQ3_XS.gguf

gguf · 10,8 GB · SHA-256 5e86bbf23195…5a21 · Hugging Face

Descargar

gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.i1-IQ3_XXS.gguf

gguf · 10,5 GB · SHA-256 c17f34650b3f…7738 · Hugging Face

Descargar

gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.i1-IQ4_XS.gguf

gguf · 13,0 GB · SHA-256 dd2fba3139e2…0414 · Hugging Face

Descargar

gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.i1-Q2_K_S.gguf

gguf · 9,89 GB · SHA-256 6a6248960215…f4f1 · Hugging Face

Descargar

gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.i1-Q2_K.gguf

gguf · 9,86 GB · SHA-256 bbe4d1d4813b…f01a · Hugging Face

Descargar

gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.i1-Q3_K_L.gguf

gguf · 12,9 GB · SHA-256 c8c864c5bdcb…c45d · Hugging Face

Descargar

gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.i1-Q3_K_M.gguf

gguf · 12,4 GB · SHA-256 61b054e2de35…db7b · Hugging Face

Descargar

gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.i1-Q3_K_S.gguf

gguf · 11,4 GB · SHA-256 250fb4a4ce0c…0e13 · Hugging Face

Descargar

gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.i1-Q4_0.gguf

gguf · 13,5 GB · SHA-256 ac7c97514d03…aa16 · Hugging Face

Descargar

gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.i1-Q4_1.gguf

gguf · 14,9 GB · SHA-256 7ff0f3dce165…ae21 · Hugging Face

Descargar

gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.i1-Q4_K_M.gguf

gguf · 15,6 GB · SHA-256 07facdc52c17…e6a3 · Hugging Face

Descargar

gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.i1-Q4_K_S.gguf

gguf · 14,4 GB · SHA-256 cd7662832572…3e03 · Hugging Face

Descargar

gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.imatrix.gguf

gguf · 54,3 MB · SHA-256 cafa70e7b701…2e44 · Hugging Face

Descargar

Extractos de fuentes

3 extractos
Readme11 julhuggingface.co/mradermacher/gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic-i1-GGUF

--- base_model: coder3101/gemma-4-26B-A4B-it-qat-q4_0-unquantized-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 IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS IQ2_S IQ1_S Q4_0 IQ3_XS Q4_1 IQ3_S --> <!-- ### quants_skip: --> <!-- ### skip_mmproj: 1 --> weighted/imatrix quants of https://huggingface.co/coder3101/gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic-GGUF **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/gemma-4-26B-A4B-it-qat-q4_0-unquantized-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-4-26B-A4B-it-qat-q4_0-unquantized-heretic-i1-GGUF/resolve/main/gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.imatrix.gguf) | imatrix | 0.2 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic-i1-GGUF/resolve/main/gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.i1-IQ1_S.gguf) | i1-IQ1_S | 8.4 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic-i1-GGUF/resolve/main/gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.i1-IQ1_M.gguf) | i1-IQ1_M | 8.8 | mostly desperate | |...

Note3 octhuggingface.co/mradermacher/gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic-i1-GGUF

Source context: 1462 downloads · 8 likes · Library transformers · Repo mradermacher/gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic-i1-GGUF

Note17 julhuggingface.co/mradermacher/gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic-i1-GGUF

Source context: 1945 downloads · 5 likes · Library transformers · Repo mradermacher/gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic-i1-GGUF