Llama PLLuM 70B Base 2412 I1 GGUF
For a convenient overview and download list, visit our model page for this model.
Source du modèle
- Type
- Other
- Taille du fichier
- 23,8 MB–53,9 GB
- Modèle de base
- CYFRAGOVPL/Llama-PLLuM-70B-base-2412
- Version
- vRevision 6d7bae6
- Mis à jour
- 2 oct. 2026
- Éditeur
- @mradermacher
- Téléchargements
- 983
- Paramètres
- 70B
- Source
- Hugging Face
Description de la source
About
weighted/imatrix quants of https://huggingface.co/CYFRAGOVPL/Llama-PLLuM-70B-base-2412
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/Llama-PLLuM-70B-base-2412-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 | 15.4 | for the desperate |
| GGUF | i1-IQ1_M | 16.9 | mostly desperate |
| GGUF | i1-IQ2_XXS | 19.2 | |
| GGUF | i1-IQ2_XS | 21.2 | |
| GGUF | i1-IQ2_S | 22.3 | |
| GGUF | i1-IQ2_M | 24.2 | |
| GGUF | i1-Q2_K_S | 24.6 | very low quality |
| GGUF | i1-Q2_K | 26.5 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 27.6 | lower quality |
| GGUF | i1-IQ3_XS | 29.4 | |
| GGUF | i1-IQ3_S | 31.0 | beats Q3_K* |
| GGUF | i1-Q3_K_S | 31.0 | IQ3_XS probably better |
| GGUF | i1-IQ3_M | 32.0 | |
| GGUF | i1-Q3_K_M | 34.4 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 37.2 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 38.0 | |
| GGUF | i1-Q4_0 | 40.2 | fast, low quality |
| GGUF | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 42.6 | fast, recommended |
| GGUF | i1-Q4_1 | 44.4 | |
| GGUF | i1-Q5_K_S | 48.8 | |
| GGUF | i1-Q5_K_M | 50.0 | |
| GGUF | i1-Q6_K | 58.0 | 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 2 oct.
Artefacts du modèle
24 artefacts
Artefacts du modèle
24 artefactsLlama-PLLuM-70B-base-2412.i1-IQ1_M.gguf
gguf · 15,6 GB · SHA-256 ef1d3f842e95…5eff · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.i1-IQ1_S.gguf
gguf · 14,3 GB · SHA-256 c718f309e551…2bf9 · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.i1-IQ2_M.gguf
gguf · 22,5 GB · SHA-256 cbdaf569e31d…eb78 · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.i1-IQ2_S.gguf
gguf · 20,7 GB · SHA-256 6101f2297cfb…3d1c · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.i1-IQ2_XS.gguf
gguf · 19,7 GB · SHA-256 6b9d85ddb4a9…9a27 · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.i1-IQ2_XXS.gguf
gguf · 17,8 GB · SHA-256 d3eeae765a4c…9ac2 · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.i1-IQ3_M.gguf
gguf · 29,7 GB · SHA-256 cff6471cc3a0…5413 · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.i1-IQ3_S.gguf
gguf · 28,8 GB · SHA-256 1d786d6bd09d…e7f5 · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.i1-IQ3_XS.gguf
gguf · 27,3 GB · SHA-256 2730a3c75d2e…0a14 · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.i1-IQ3_XXS.gguf
gguf · 25,6 GB · SHA-256 79608587ecba…2471 · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.i1-IQ4_XS.gguf
gguf · 35,3 GB · SHA-256 6dd0a9e8b87a…b11a · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.i1-Q2_K_S.gguf
gguf · 22,8 GB · SHA-256 36fe6a3b3d90…65d5 · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.i1-Q2_K.gguf
gguf · 24,6 GB · SHA-256 93770654ab5d…1053 · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.i1-Q3_K_L.gguf
gguf · 34,6 GB · SHA-256 9c854bb4a26b…959d · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.i1-Q3_K_M.gguf
gguf · 31,9 GB · SHA-256 cdb8eb46e704…f841 · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.i1-Q3_K_S.gguf
gguf · 28,8 GB · SHA-256 8f9dcb152699…9607 · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.i1-Q4_0.gguf
gguf · 37,4 GB · SHA-256 f733c4211b72…9d20 · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.i1-Q4_1.gguf
gguf · 41,3 GB · SHA-256 84fb4f34e18a…3e24 · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.i1-Q4_K_M.gguf
gguf · 39,6 GB · SHA-256 0a29b6a7d5a2…4297 · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.i1-Q4_K_S.gguf
gguf · 37,6 GB · SHA-256 b5148919f59b…5256 · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.i1-Q5_K_M.gguf
gguf · 46,5 GB · SHA-256 da78ef058559…e400 · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.i1-Q5_K_S.gguf
gguf · 45,3 GB · SHA-256 db1c41619bfc…2c74 · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.i1-Q6_K.gguf
gguf · 53,9 GB · SHA-256 fa4ef75b8c68…d16f · Hugging Face
TéléchargerLlama-PLLuM-70B-base-2412.imatrix.gguf
gguf · 23,8 MB · SHA-256 707c16e1bec9…e254 · Hugging Face
TéléchargerExtraits de sources
3 extraits
Extraits de sources
3 extraits--- base_model: CYFRAGOVPL/Llama-PLLuM-70B-base-2412 language: - pl library_name: transformers license: llama3.1 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/CYFRAGOVPL/Llama-PLLuM-70B-base-2412 <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-PLLuM-70B-base-2412-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/Llama-PLLuM-70B-base-2412-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/Llama-PLLuM-70B-base-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-base-2412.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-base-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-base-2412.i1-IQ1_S.gguf) | i1-IQ1_S | 15.4 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-base-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-base-2412.i1-IQ1_M.gguf) | i1-IQ1_M | 16.9 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-base-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-base-2412.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 19.2 | | | [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-base-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-base-2412.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.2 | | | [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-base-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-base-2412.i1-IQ2_S.gguf) | i1-IQ2_S | 22.3 | | | [GGUF](https://huggingface.co/mra...
Source context: 983 downloads · 0 likes · Library transformers · Repo mradermacher/Llama-PLLuM-70B-base-2412-i1-GGUF
Source context: 149 downloads · 0 likes · Library transformers · Repo mradermacher/Llama-PLLuM-70B-base-2412-i1-GGUF
