Rocinante XL 16B v1 Absolute Heresy GGUF
For a convenient overview and download list, visit our model page for this model.
Source du modèle
- Type
- Other
- Taille du fichier
- 5,77–15,9 GB
- Modèle de base
- MuXodious/Rocinante-XL-16B-v1-absolute-heresy
- Version
- vRevision 4048c71
- Mis à jour
- 8 oct. 2026
- Éditeur
- @mradermacher
- Téléchargements
- 450
- Paramètres
- 16B
- Source
- Hugging Face
Description de la source
About
static quants of https://huggingface.co/MuXodious/Rocinante-XL-16B-v1-absolute-heresy
For a convenient overview and download list, visit our model page for this model.
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Rocinante-XL-16B-v1-absolute-heresy-i1-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)
| Link | Type | Size/GB | Notes |
|---|---|---|---|
| GGUF | Q2_K | 6.3 | |
| GGUF | Q3_K_S | 7.3 | |
| GGUF | Q3_K_M | 8.0 | lower quality |
| GGUF | Q3_K_L | 8.7 | |
| GGUF | IQ4_XS | 9.0 | |
| GGUF | Q4_K_S | 9.4 | fast, recommended |
| GGUF | Q4_K_M | 9.8 | fast, recommended |
| GGUF | Q5_K_S | 11.2 | |
| GGUF | Q5_K_M | 11.5 | |
| GGUF | Q6_K | 13.3 | very good quality |
| GGUF | Q8_0 | 17.2 | fast, best quality |
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.
Sources
1 source
Sources
1 sourceVérifié 14 sept.
Artefacts du modèle
11 artefacts
Artefacts du modèle
11 artefactsRocinante-XL-16B-v1-absolute-heresy.IQ4_XS.gguf
gguf · 8,24 GB · SHA-256 9964af40f2fd…f118 · Hugging Face
TéléchargerRocinante-XL-16B-v1-absolute-heresy.Q2_K.gguf
gguf · 5,77 GB · SHA-256 98650713f28c…fc2c · Hugging Face
TéléchargerRocinante-XL-16B-v1-absolute-heresy.Q3_K_L.gguf
gguf · 7,97 GB · SHA-256 442985349526…47c0 · Hugging Face
TéléchargerRocinante-XL-16B-v1-absolute-heresy.Q3_K_M.gguf
gguf · 7,37 GB · SHA-256 04b8d04f4450…d93a · Hugging Face
TéléchargerRocinante-XL-16B-v1-absolute-heresy.Q3_K_S.gguf
gguf · 6,68 GB · SHA-256 af53c12bb1d5…ac63 · Hugging Face
TéléchargerRocinante-XL-16B-v1-absolute-heresy.Q4_K_M.gguf
gguf · 9,08 GB · SHA-256 1d7dc138a781…0acc · Hugging Face
TéléchargerRocinante-XL-16B-v1-absolute-heresy.Q4_K_S.gguf
gguf · 8,64 GB · SHA-256 7a8f8a8bf964…f6af · Hugging Face
TéléchargerRocinante-XL-16B-v1-absolute-heresy.Q5_K_M.gguf
gguf · 10,6 GB · SHA-256 b0fafa5f876d…8632 · Hugging Face
TéléchargerRocinante-XL-16B-v1-absolute-heresy.Q5_K_S.gguf
gguf · 10,4 GB · SHA-256 477b6213bc9c…8a89 · Hugging Face
TéléchargerRocinante-XL-16B-v1-absolute-heresy.Q6_K.gguf
gguf · 12,3 GB · SHA-256 a0130e806892…ee80 · Hugging Face
TéléchargerRocinante-XL-16B-v1-absolute-heresy.Q8_0.gguf
gguf · 15,9 GB · SHA-256 f67a0f461267…cf41 · Hugging Face
TéléchargerExtraits de sources
3 extraits
Extraits de sources
3 extraits--- base_model: MuXodious/Rocinante-XL-16B-v1-absolute-heresy language: - en library_name: transformers mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - heretic - uncensored - decensored - abliterated --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> <!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS --> <!-- ### quants_skip: --> <!-- ### skip_mmproj: --> static quants of https://huggingface.co/MuXodious/Rocinante-XL-16B-v1-absolute-heresy <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Rocinante-XL-16B-v1-absolute-heresy-GGUF).*** weighted/imatrix quants are available at https://huggingface.co/mradermacher/Rocinante-XL-16B-v1-absolute-heresy-i1-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/Rocinante-XL-16B-v1-absolute-heresy-GGUF/resolve/main/Rocinante-XL-16B-v1-absolute-heresy.Q2_K.gguf) | Q2_K | 6.3 | | | [GGUF](https://huggingface.co/mradermacher/Rocinante-XL-16B-v1-absolute-heresy-GGUF/resolve/main/Rocinante-XL-16B-v1-absolute-heresy.Q3_K_S.gguf) | Q3_K_S | 7.3 | | | [GGUF](https://huggingface.co/mradermacher/Rocinante-XL-16B-v1-absolute-heresy-GGUF/resolve/main/Rocinante-XL-16B-v1-absolute-heresy.Q3_K_M.gguf) | Q3_K_M | 8.0 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Rocinante-XL-16B-v1-absolute-heresy-GGUF/resolve/main/Rocinante-XL-16B-v1-absolute-heresy.Q3_K_L.gguf) | Q3_K_L | 8.7 | | | [GGUF](https://huggingface.co/mradermacher/Rocinante-XL-16B-v1-absolute-heresy-GGUF/resolve/main/Rocinante-XL-16B-v1-absolute-heresy.IQ4_XS.gguf) | IQ4_XS | 9.0 | | | [GGUF](https://huggingface.co/mradermacher/Rocinante-XL-16B-v1-absolute-heresy-GGUF/resolve/main/Rocinante-XL-16B-v1-absolute-heresy.Q4_K_S.gguf) | Q4_K_S | 9.4 | fast, recommended | | [GGUF](https://huggingface.co/mra...
Source context: 450 downloads · 3 likes · Library transformers · Repo mradermacher/Rocinante-XL-16B-v1-absolute-heresy-GGUF
Source context: 127 downloads · 3 likes · Library transformers · Repo mradermacher/Rocinante-XL-16B-v1-absolute-heresy-GGUF
