Aller au contenu
ModelVérifiéExterne
Télécharger

MiniMax M2.7 Abliterated BF16 I1 GGUF

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

Sourcehuggingface.co/mradermacher/MiniMax-M2.7-abliterated-BF16-i1-GGUF/tree/2aebfbbb74d26c613b0ea98888f1802144493db4
TypeOtherModèle de baseYoussofal/MiniMax-M2.7-abliterated-BF16VersionRevision 2aebfbbÉditeur@mradermacherCClasse

Source du modèle

Type
Other
Taille du fichier
470 MB–91,9 GB
Modèle de base
Youssofal/MiniMax-M2.7-abliterated-BF16
Version
vRevision 2aebfbb
Mis à jour
2 oct. 2026
Éditeur
@mradermacher
Téléchargements
421
Tâches
Génération de texte
Source
Hugging Face

Description de la source

About

weighted/imatrix quants of https://huggingface.co/Youssofal/MiniMax-M2.7-abliterated-BF16

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

static quants are available at https://huggingface.co/mradermacher/MiniMax-M2.7-abliterated-BF16-GGUF

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
GGUFimatrix0.6imatrix file (for creating your own quants)
GGUFi1-IQ1_S46.6for the desperate
GGUFi1-IQ1_M51.7mostly desperate
GGUFi1-IQ2_XXS60.2
GGUFi1-IQ2_XS67.1
GGUFi1-IQ2_S68.1
GGUFi1-IQ2_M74.9
GGUFi1-Q2_K_S77.7very low quality
GGUFi1-Q2_K83.4IQ3_XXS probably better
GGUFi1-IQ3_XXS88.1lower quality
GGUFi1-IQ3_XS93.4
GGUFi1-Q3_K_S98.8IQ3_XS probably better
GGUFi1-IQ3_S98.8beats Q3_K*
PART 1 PART 2 PART 3i1-IQ3_M100.1
PART 1 PART 2 PART 3i1-Q3_K_M109.4IQ3_S probably better
PART 1 PART 2 PART 3i1-Q3_K_L118.5IQ3_M probably better
PART 1 PART 2 PART 3i1-IQ4_XS122.0
PART 1 PART 2 PART 3i1-Q4_0129.6fast, low quality
PART 1 PART 2 PART 3i1-Q4_K_S130.1optimal size/speed/quality
PART 1 PART 2 PART 3i1-Q4_K_M138.4fast, recommended
PART 1 PART 2 PART 3i1-Q4_1143.3
PART 1 PART 2 PART 3 PART 4i1-Q5_K_S157.6
PART 1 PART 2 PART 3 PART 4i1-Q5_K_M162.4
PART 1 PART 2 PART 3 PART 4i1-Q6_K187.9practically 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 2aebfbbb74d26c613b0ea98888f1802144493db4
huggingface.co/mradermacher/MiniMax-M2.7-abliterated-BF16-i1-GGUF/tree/2aebfbbb74d26c613b0ea98888f1802144493db4

Vérifié 2 oct.

Artefacts du modèle

13 artefacts

MiniMax-M2.7-abliterated-BF16.i1-IQ1_M.gguf

gguf · 48,1 GB · SHA-256 2b71ca46d936…8ef7 · Hugging Face

Télécharger

MiniMax-M2.7-abliterated-BF16.i1-IQ1_S.gguf

gguf · 43,3 GB · SHA-256 48d14d604df3…178a · Hugging Face

Télécharger

MiniMax-M2.7-abliterated-BF16.i1-IQ2_M.gguf

gguf · 69,7 GB · SHA-256 9ab33c7d0f0e…bcba · Hugging Face

Télécharger

MiniMax-M2.7-abliterated-BF16.i1-IQ2_S.gguf

gguf · 63,4 GB · SHA-256 8fa602990c3b…4582 · Hugging Face

Télécharger

MiniMax-M2.7-abliterated-BF16.i1-IQ2_XS.gguf

gguf · 62,4 GB · SHA-256 b01d5a99a4e1…214f · Hugging Face

Télécharger

MiniMax-M2.7-abliterated-BF16.i1-IQ2_XXS.gguf

gguf · 56,0 GB · SHA-256 a45491f32197…7b30 · Hugging Face

Télécharger

MiniMax-M2.7-abliterated-BF16.i1-IQ3_S.gguf

gguf · 91,9 GB · SHA-256 a2355e51400b…a47c · Hugging Face

Télécharger

MiniMax-M2.7-abliterated-BF16.i1-IQ3_XS.gguf

gguf · 86,9 GB · SHA-256 3c8cadedd433…69df · Hugging Face

Télécharger

MiniMax-M2.7-abliterated-BF16.i1-IQ3_XXS.gguf

gguf · 81,9 GB · SHA-256 80dacd0b0089…c85c · Hugging Face

Télécharger

MiniMax-M2.7-abliterated-BF16.i1-Q2_K_S.gguf

gguf · 72,2 GB · SHA-256 6ea7f68ae993…37d6 · Hugging Face

Télécharger

MiniMax-M2.7-abliterated-BF16.i1-Q2_K.gguf

gguf · 77,6 GB · SHA-256 b35653157f94…a8cf · Hugging Face

Télécharger

MiniMax-M2.7-abliterated-BF16.i1-Q3_K_S.gguf

gguf · 91,9 GB · SHA-256 ac595d408b8a…8736 · Hugging Face

Télécharger

MiniMax-M2.7-abliterated-BF16.imatrix.gguf

gguf · 470 MB · SHA-256 fb706691e056…f91a · Hugging Face

Télécharger

Extraits de sources

3 extraits
Readme11 juil.huggingface.co/mradermacher/MiniMax-M2.7-abliterated-BF16-i1-GGUF

--- base_model: Youssofal/MiniMax-M2.7-abliterated-BF16 language: - en library_name: transformers license: other mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - minimax - minimax_m2 - moe - abliterated - heretic - ara - bf16 - custom_code - text-generation --- ## 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/Youssofal/MiniMax-M2.7-abliterated-BF16 <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MiniMax-M2.7-abliterated-BF16-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/MiniMax-M2.7-abliterated-BF16-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/MiniMax-M2.7-abliterated-BF16-i1-GGUF/resolve/main/MiniMax-M2.7-abliterated-BF16.imatrix.gguf) | imatrix | 0.6 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/MiniMax-M2.7-abliterated-BF16-i1-GGUF/resolve/main/MiniMax-M2.7-abliterated-BF16.i1-IQ1_S.gguf) | i1-IQ1_S | 46.6 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/MiniMax-M2.7-abliterated-BF16-i1-GGUF/resolve/main/MiniMax-M2.7-abliterated-BF16.i1-IQ1_M.gguf) | i1-IQ1_M | 51.7 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/MiniMax-M2.7-abliterated-BF16-i1-GGUF/resolve/main/MiniMax-M2.7-abliterated-BF16.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 60.2 | | | [GGUF](https://huggingface.co/mradermacher/MiniMax-M2.7-abliterated-BF16-i1-GGUF/resolve/main/MiniMax-M2.7-abliterated-BF16.i1-IQ2_XS.gguf) | i1-IQ2_XS | 67.1 | | | [GGUF](https://huggingface.co/mra...

Note2 oct.huggingface.co/mradermacher/MiniMax-M2.7-abliterated-BF16-i1-GGUF

Source context: 421 downloads · 1 likes · Pipeline text-generation · Library transformers · Repo mradermacher/MiniMax-M2.7-abliterated-BF16-i1-GGUF

Note17 juil.huggingface.co/mradermacher/MiniMax-M2.7-abliterated-BF16-i1-GGUF

Source context: 121 downloads · 1 likes · Pipeline text-generation · Library transformers · Repo mradermacher/MiniMax-M2.7-abliterated-BF16-i1-GGUF