Apertus 8B MeditronFO I1 GGUF
For a convenient overview and download list, visit our model page for this model.
Source du modèle
- Type
- Text model
- Taille du fichier
- 5,15 MB–6,16 GB
- Modèle de base
- EPFLiGHT/Apertus-8B-MeditronFO
- Version
- vRevision e5abb13
- Mis à jour
- 3 oct. 2026
- Éditeur
- @mradermacher
- Téléchargements
- 1,3 k
- Paramètres
- 8B
- Source
- Hugging Face
Description de la source
About
weighted/imatrix quants of https://huggingface.co/EPFLiGHT/Apertus-8B-MeditronFO
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/Apertus-8B-MeditronFO-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 | imatrix | 0.1 | imatrix file (for creating your own quants) |
| GGUF | i1-IQ1_S | 2.1 | for the desperate |
| GGUF | i1-IQ1_M | 2.3 | mostly desperate |
| GGUF | i1-IQ2_XXS | 2.5 | |
| GGUF | i1-IQ2_XS | 2.7 | |
| GGUF | i1-IQ2_S | 2.9 | |
| GGUF | i1-IQ2_M | 3.1 | |
| GGUF | i1-Q2_K_S | 3.1 | very low quality |
| GGUF | i1-IQ3_XXS | 3.4 | lower quality |
| GGUF | i1-Q2_K | 3.4 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XS | 3.7 | |
| GGUF | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
| GGUF | i1-IQ3_S | 3.8 | beats Q3_K* |
| GGUF | i1-IQ3_M | 3.9 | |
| GGUF | i1-Q3_K_M | 4.3 | IQ3_S probably better |
| GGUF | i1-IQ4_XS | 4.6 | |
| GGUF | i1-Q3_K_L | 4.7 | IQ3_M probably better |
| GGUF | i1-IQ4_NL | 4.8 | prefer IQ4_XS |
| GGUF | i1-Q4_0 | 4.8 | fast, low quality |
| GGUF | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 5.2 | fast, recommended |
| GGUF | i1-Q4_1 | 5.2 | |
| GGUF | i1-Q5_K_S | 5.7 | |
| GGUF | i1-Q5_K_M | 5.9 | |
| GGUF | i1-Q6_K | 6.7 | practically 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
Sources
1 sourceVérifié 3 oct.
Artefacts du modèle
25 artefacts
Artefacts du modèle
25 artefactsApertus-8B-MeditronFO.i1-IQ1_M.gguf
gguf · 2,04 GB · SHA-256 bfe9a385f452…d8b6 · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-IQ1_S.gguf
gguf · 1,91 GB · SHA-256 2572d61219b3…feef · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-IQ2_M.gguf
gguf · 2,77 GB · SHA-256 b637002f2509…d44d · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-IQ2_S.gguf
gguf · 2,60 GB · SHA-256 36153613d3d6…4344 · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-IQ2_XS.gguf
gguf · 2,44 GB · SHA-256 ff7594bc9727…ade7 · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-IQ2_XXS.gguf
gguf · 2,25 GB · SHA-256 049139df5e97…fc41 · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-IQ3_M.gguf
gguf · 3,55 GB · SHA-256 0c7dfa66cc6a…66b8 · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-IQ3_S.gguf
gguf · 3,44 GB · SHA-256 37e53c09d75d…5eb1 · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-IQ3_XS.gguf
gguf · 3,32 GB · SHA-256 928bafaee604…a5b1 · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-IQ3_XXS.gguf
gguf · 3,06 GB · SHA-256 3168e877bdf4…0c86 · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-IQ4_NL.gguf
gguf · 4,37 GB · SHA-256 8f0b2c870f5c…e49b · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-IQ4_XS.gguf
gguf · 4,16 GB · SHA-256 d77691f0ed27…7b51 · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-Q2_K_S.gguf
gguf · 2,82 GB · SHA-256 0cf4db330008…99c9 · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-Q2_K.gguf
gguf · 3,06 GB · SHA-256 9a542c020972…0a03 · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-Q3_K_L.gguf
gguf · 4,26 GB · SHA-256 3363117b4832…3230 · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-Q3_K_M.gguf
gguf · 3,88 GB · SHA-256 ac22e3cb756e…4940 · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-Q3_K_S.gguf
gguf · 3,43 GB · SHA-256 07840df6b3ec…93a8 · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-Q4_0.gguf
gguf · 4,38 GB · SHA-256 66f59a739c8b…23a6 · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-Q4_1.gguf
gguf · 4,79 GB · SHA-256 86e9f28090d2…b8cb · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-Q4_K_M.gguf
gguf · 4,71 GB · SHA-256 6253b025fec2…cf60 · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-Q4_K_S.gguf
gguf · 4,40 GB · SHA-256 8aa13e2c52d0…0dee · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-Q5_K_M.gguf
gguf · 5,41 GB · SHA-256 05b2c67c8acd…d67f · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-Q5_K_S.gguf
gguf · 5,23 GB · SHA-256 5e6d73886929…eed5 · Hugging Face
TéléchargerApertus-8B-MeditronFO.i1-Q6_K.gguf
gguf · 6,16 GB · SHA-256 b57f55b125e2…a122 · Hugging Face
TéléchargerApertus-8B-MeditronFO.imatrix.gguf
gguf · 5,15 MB · SHA-256 fae71d21a424…d447 · Hugging Face
TéléchargerExtraits de sources
3 extraits
Extraits de sources
3 extraits--- base_model: EPFLiGHT/Apertus-8B-MeditronFO datasets: - EPFLiGHT/fully-open-meditron language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - medical - clinical - healthcare - meditron - fully-open - medical-llm --- ## 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/EPFLiGHT/Apertus-8B-MeditronFO <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Apertus-8B-MeditronFO-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/Apertus-8B-MeditronFO-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/Apertus-8B-MeditronFO-i1-GGUF/resolve/main/Apertus-8B-MeditronFO.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/Apertus-8B-MeditronFO-i1-GGUF/resolve/main/Apertus-8B-MeditronFO.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Apertus-8B-MeditronFO-i1-GGUF/resolve/main/Apertus-8B-MeditronFO.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/Apertus-8B-MeditronFO-i1-GGUF/resolve/main/Apertus-8B-MeditronFO.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | | [GGUF](https://huggingface.co/mradermacher/Apertus-8B-MeditronFO-i1-GGUF/resolve/main/Apertus-8B-MeditronFO.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | | [GGUF](https://huggingface.co/mradermacher/Apertus-8B-MeditronFO-i1-GGUF/resolve/main/Apertus-8B-MeditronFO.i1-IQ2_S.gguf) | i1-IQ2...
Source context: 1258 downloads · 1 likes · Library transformers · Repo mradermacher/Apertus-8B-MeditronFO-i1-GGUF
Source context: 1215 downloads · 1 likes · Library transformers · Repo mradermacher/Apertus-8B-MeditronFO-i1-GGUF
