Aller au contenu
ModelVérifiéExterne
Télécharger

DNA3.0 35B A3B I1 GGUF

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

Sourcehuggingface.co/mradermacher/DNA3.0-35B-A3B-i1-GGUF/tree/c86e86b5b18432b76b87040ad12865199092a688
TypeOtherModèle de basednotitia/DNA3.0-35B-A3BVersionRevision c86e86bÉditeur@mradermacherCClasse

Source du modèle

Type
Other
Taille du fichier
183 MB–27,2 GB
Modèle de base
dnotitia/DNA3.0-35B-A3B
Version
vRevision c86e86b
Mis à jour
3 oct. 2026
Éditeur
@mradermacher
Téléchargements
446
Paramètres
35B
Source
Hugging Face

Description de la source

About

weighted/imatrix quants of https://huggingface.co/dnotitia/DNA3.0-35B-A3B

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

static quants are available at https://huggingface.co/mradermacher/DNA3.0-35B-A3B-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
GGUFimatrix0.3imatrix file (for creating your own quants)
GGUFi1-Q2_K13.3IQ3_XXS probably better
GGUFi1-Q3_K_S15.6IQ3_XS probably better
GGUFi1-IQ3_S15.7beats Q3_K*
GGUFi1-IQ3_M15.9
GGUFi1-Q3_K_M17.3IQ3_S probably better
GGUFi1-Q3_K_L18.7IQ3_M probably better
GGUFi1-IQ4_XS19.3
GGUFi1-Q4_020.4fast, low quality
GGUFi1-Q4_K_S20.5optimal size/speed/quality
GGUFi1-Q4_K_M21.8fast, recommended
GGUFi1-Q4_122.5
GGUFi1-Q5_K_S24.7
GGUFi1-Q5_K_M25.4
GGUFi1-Q6_K29.3practically 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 c86e86b5b18432b76b87040ad12865199092a688
huggingface.co/mradermacher/DNA3.0-35B-A3B-i1-GGUF/tree/c86e86b5b18432b76b87040ad12865199092a688

Vérifié 3 oct.

Artefacts du modèle

15 artefacts

DNA3.0-35B-A3B.i1-IQ3_M.gguf

gguf · 14,7 GB · SHA-256 14eaf7a78d32…a85b · Hugging Face

Télécharger

DNA3.0-35B-A3B.i1-IQ3_S.gguf

gguf · 14,5 GB · SHA-256 ecec58637d65…be6d · Hugging Face

Télécharger

DNA3.0-35B-A3B.i1-IQ4_XS.gguf

gguf · 17,9 GB · SHA-256 7361c408b91f…8779 · Hugging Face

Télécharger

DNA3.0-35B-A3B.i1-Q2_K.gguf

gguf · 12,3 GB · SHA-256 45055acd2bf9…7d3e · Hugging Face

Télécharger

DNA3.0-35B-A3B.i1-Q3_K_L.gguf

gguf · 17,3 GB · SHA-256 bfba27d70410…3b20 · Hugging Face

Télécharger

DNA3.0-35B-A3B.i1-Q3_K_M.gguf

gguf · 16,0 GB · SHA-256 5d85f671216b…1c3e · Hugging Face

Télécharger

DNA3.0-35B-A3B.i1-Q3_K_S.gguf

gguf · 14,5 GB · SHA-256 133ade536378…90c8 · Hugging Face

Télécharger

DNA3.0-35B-A3B.i1-Q4_0.gguf

gguf · 18,9 GB · SHA-256 d9bf0b8183f7…2625 · Hugging Face

Télécharger

DNA3.0-35B-A3B.i1-Q4_1.gguf

gguf · 20,8 GB · SHA-256 0727ea325ad8…d92a · Hugging Face

Télécharger

DNA3.0-35B-A3B.i1-Q4_K_M.gguf

gguf · 20,2 GB · SHA-256 ba8195cbad89…bf43 · Hugging Face

Télécharger

DNA3.0-35B-A3B.i1-Q4_K_S.gguf

gguf · 19,0 GB · SHA-256 cfef686bfefe…582e · Hugging Face

Télécharger

DNA3.0-35B-A3B.i1-Q5_K_M.gguf

gguf · 23,6 GB · SHA-256 52e4d7256f96…6524 · Hugging Face

Télécharger

DNA3.0-35B-A3B.i1-Q5_K_S.gguf

gguf · 22,9 GB · SHA-256 93c25be2fec7…7ad7 · Hugging Face

Télécharger

DNA3.0-35B-A3B.i1-Q6_K.gguf

gguf · 27,2 GB · SHA-256 ffa6d14c164e…dffc · Hugging Face

Télécharger

DNA3.0-35B-A3B.imatrix.gguf

gguf · 183 MB · SHA-256 8798cf68e8e3…ee83 · Hugging Face

Télécharger

Extraits de sources

3 extraits
Readme11 juil.huggingface.co/mradermacher/DNA3.0-35B-A3B-i1-GGUF

--- base_model: dnotitia/DNA3.0-35B-A3B language: - en library_name: transformers license: apache-2.0 license_link: https://huggingface.co/dnotitia/DNA3.0-35B-A3B/blob/main/LICENSE 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/dnotitia/DNA3.0-35B-A3B <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DNA3.0-35B-A3B-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/DNA3.0-35B-A3B-GGUF **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/DNA3.0-35B-A3B-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/DNA3.0-35B-A3B-i1-GGUF/resolve/main/DNA3.0-35B-A3B.imatrix.gguf) | imatrix | 0.3 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/DNA3.0-35B-A3B-i1-GGUF/resolve/main/DNA3.0-35B-A3B.i1-Q2_K.gguf) | i1-Q2_K | 13.3 | IQ3_XXS probably better | | [GGUF](https://huggingface.co/mradermacher/DNA3.0-35B-A3B-i1-GGUF/resolve/main/DNA3.0-35B-A3B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 15.6 | IQ3_XS probably better | | [GGUF](https://huggingface.co/mradermacher/DNA3.0-35B-A3B-i1-GGUF/resolve/main/DNA3.0-35B-A3B.i1-IQ3_S.gguf) | i1-IQ3_S | 15.7 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/DNA3.0-35B-A3B-i1-GGUF/resolve/main/DNA3.0-35B-A3B.i1-IQ3_M.gguf) | i1-IQ3_M | 15.9 | | | [GGUF](https://huggingface.co/mradermacher/DNA3.0-35B-A3B-i1-GGUF/resolve/main/DNA3.0-35B-A3B.i1-Q3_K_...

Note3 oct.huggingface.co/mradermacher/DNA3.0-35B-A3B-i1-GGUF

Source context: 446 downloads · 0 likes · Library transformers · Repo mradermacher/DNA3.0-35B-A3B-i1-GGUF

Note17 juil.huggingface.co/mradermacher/DNA3.0-35B-A3B-i1-GGUF

Source context: 179 downloads · 0 likes · Library transformers · Repo mradermacher/DNA3.0-35B-A3B-i1-GGUF