Saltar al contenido
ModelVerificadoExterno
Descargar

GRM 2.6 Opus Heretic Abliterated MTP I1 GGUF

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

Fuentehuggingface.co/mradermacher/GRM-2.6-Opus-Heretic-Abliterated-MTP-i1-GGUF/tree/75f6286f3fae6c232761e6d74ff198d919873915
TipoOtherModelo basedndll/GRM-2.6-Opus-Heretic-Abliterated-MTPVersiónRevision 75f6286Publicador@mradermacherCcalidad

Fuente del modelo

Tipo
Other
Tamaño del archivo
13,0 MB–20,9 GB
Modelo base
dndll/GRM-2.6-Opus-Heretic-Abliterated-MTP
Versión
vRevision 75f6286
Actualizado
3 oct 2026
Publicador
@mradermacher
Descargas
422
Fuente
Hugging Face

Descripción de la fuente

About

weighted/imatrix quants of https://huggingface.co/dndll/GRM-2.6-Opus-Heretic-Abliterated-MTP

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

static quants are available at https://huggingface.co/mradermacher/GRM-2.6-Opus-Heretic-Abliterated-MTP-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-Q2_K11.0IQ3_XXS probably better
GGUFi1-Q3_K_S12.4IQ3_XS probably better
GGUFi1-IQ3_S12.7beats Q3_K*
GGUFi1-IQ3_M12.9
GGUFi1-Q3_K_M13.6IQ3_S probably better
GGUFi1-Q3_K_L14.7IQ3_M probably better
GGUFi1-IQ4_XS15.4
GGUFi1-Q4_015.9fast, low quality
GGUFi1-Q4_K_S15.9optimal size/speed/quality
GGUFi1-Q4_K_M16.9fast, recommended
GGUFi1-Q4_117.4
GGUFi1-Q5_K_S19.1
GGUFi1-Q5_K_M19.6
GGUFi1-Q6_K22.5practically 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.

Fuentes

1 fuente
Hugging FacePrincipalVersión 75f6286f3fae6c232761e6d74ff198d919873915
huggingface.co/mradermacher/GRM-2.6-Opus-Heretic-Abliterated-MTP-i1-GGUF/tree/75f6286f3fae6c232761e6d74ff198d919873915

Verificado 3 oct

Artefactos del modelo

15 artefactos

GRM-2.6-Opus-Heretic-Abliterated-MTP.i1-IQ3_M.gguf

gguf · 11,9 GB · SHA-256 efa18187f5f7…c81d · Hugging Face

Descargar

GRM-2.6-Opus-Heretic-Abliterated-MTP.i1-IQ3_S.gguf

gguf · 11,7 GB · SHA-256 46eeec22bfeb…bf15 · Hugging Face

Descargar

GRM-2.6-Opus-Heretic-Abliterated-MTP.i1-IQ4_XS.gguf

gguf · 14,3 GB · SHA-256 e666151e025f…ac77 · Hugging Face

Descargar

GRM-2.6-Opus-Heretic-Abliterated-MTP.i1-Q2_K.gguf

gguf · 10,1 GB · SHA-256 5e1d2c09fdfc…45e4 · Hugging Face

Descargar

GRM-2.6-Opus-Heretic-Abliterated-MTP.i1-Q3_K_L.gguf

gguf · 13,6 GB · SHA-256 2e068917954f…3c35 · Hugging Face

Descargar

GRM-2.6-Opus-Heretic-Abliterated-MTP.i1-Q3_K_M.gguf

gguf · 12,6 GB · SHA-256 5e1abb6e19c2…3054 · Hugging Face

Descargar

GRM-2.6-Opus-Heretic-Abliterated-MTP.i1-Q3_K_S.gguf

gguf · 11,4 GB · SHA-256 c06f5361f463…8ee3 · Hugging Face

Descargar

GRM-2.6-Opus-Heretic-Abliterated-MTP.i1-Q4_0.gguf

gguf · 14,7 GB · SHA-256 eea41b0ee626…8685 · Hugging Face

Descargar

GRM-2.6-Opus-Heretic-Abliterated-MTP.i1-Q4_1.gguf

gguf · 16,2 GB · SHA-256 d721cd85c7d4…741f · Hugging Face

Descargar

GRM-2.6-Opus-Heretic-Abliterated-MTP.i1-Q4_K_M.gguf

gguf · 15,7 GB · SHA-256 9d33a7f99fb6…d918 · Hugging Face

Descargar

GRM-2.6-Opus-Heretic-Abliterated-MTP.i1-Q4_K_S.gguf

gguf · 14,7 GB · SHA-256 4f7a93b98309…f614 · Hugging Face

Descargar

GRM-2.6-Opus-Heretic-Abliterated-MTP.i1-Q5_K_M.gguf

gguf · 18,2 GB · SHA-256 c957c4b2be7d…f82a · Hugging Face

Descargar

GRM-2.6-Opus-Heretic-Abliterated-MTP.i1-Q5_K_S.gguf

gguf · 17,7 GB · SHA-256 14ef2304d2c3…4dbc · Hugging Face

Descargar

GRM-2.6-Opus-Heretic-Abliterated-MTP.i1-Q6_K.gguf

gguf · 20,9 GB · SHA-256 46f73fe3561a…6834 · Hugging Face

Descargar

GRM-2.6-Opus-Heretic-Abliterated-MTP.imatrix.gguf

gguf · 13,0 MB · SHA-256 dcac9dfa5f73…0017 · Hugging Face

Descargar

Extractos de fuentes

3 extractos
Readme11 julhuggingface.co/mradermacher/GRM-2.6-Opus-Heretic-Abliterated-MTP-i1-GGUF

--- base_model: dndll/GRM-2.6-Opus-Heretic-Abliterated-MTP language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher --- ## 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/dndll/GRM-2.6-Opus-Heretic-Abliterated-MTP <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GRM-2.6-Opus-Heretic-Abliterated-MTP-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/GRM-2.6-Opus-Heretic-Abliterated-MTP-GGUF **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/GRM-2.6-Opus-Heretic-Abliterated-MTP-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/GRM-2.6-Opus-Heretic-Abliterated-MTP-i1-GGUF/resolve/main/GRM-2.6-Opus-Heretic-Abliterated-MTP.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/GRM-2.6-Opus-Heretic-Abliterated-MTP-i1-GGUF/resolve/main/GRM-2.6-Opus-Heretic-Abliterated-MTP.i1-Q2_K.gguf) | i1-Q2_K | 11.0 | IQ3_XXS probably better | | [GGUF](https://huggingface.co/mradermacher/GRM-2.6-Opus-Heretic-Abliterated-MTP-i1-GGUF/resolve/main/GRM-2.6-Opus-Heretic-Abliterated-MTP.i1-Q3_K_S.gguf) | i1-Q3_K_S | 12.4 | IQ3_XS probably better | | [GGUF](https://huggingface.co/mradermacher/GRM-2.6-Opus-Heretic-Abliterated-MTP-i1-GGUF/resolve/main/GRM-2.6-Opus-Heretic-Abliterated-MTP.i1-IQ3_S.gguf) | i1-IQ3_S | 12.7 | beats Q3_K* | | [GGUF](https://huggingface.co/mrad...

Note3 octhuggingface.co/mradermacher/GRM-2.6-Opus-Heretic-Abliterated-MTP-i1-GGUF

Source context: 422 downloads · 0 likes · Library transformers · Repo mradermacher/GRM-2.6-Opus-Heretic-Abliterated-MTP-i1-GGUF

Note17 julhuggingface.co/mradermacher/GRM-2.6-Opus-Heretic-Abliterated-MTP-i1-GGUF

Source context: 105 downloads · 0 likes · Library transformers · Repo mradermacher/GRM-2.6-Opus-Heretic-Abliterated-MTP-i1-GGUF