PLLuM 8x7B Chat 2412 I1 GGUF
For a convenient overview and download list, visit our model page for this model.
Model source
- Kind
- Other
- File size
- 24.5 MB–35.7 GB
- Base model
- CYFRAGOVPL/PLLuM-8x7B-chat-2412
- Version
- vRevision 76fd987
- Updated
- Nov 4, 2026
- Publisher
- @mradermacher
- Downloads
- 830
- Source
- Hugging Face
Source description
About
weighted/imatrix quants of https://huggingface.co/CYFRAGOVPL/PLLuM-8x7B-chat-2412
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/PLLuM-8x7B-chat-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 | 9.9 | for the desperate |
| GGUF | i1-IQ1_M | 10.9 | mostly desperate |
| GGUF | i1-IQ2_XXS | 12.7 | |
| GGUF | i1-IQ2_XS | 14.0 | |
| GGUF | i1-IQ2_S | 14.2 | |
| GGUF | i1-IQ2_M | 15.6 | |
| GGUF | i1-Q2_K_S | 16.1 | very low quality |
| GGUF | i1-Q2_K | 17.4 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 18.3 | lower quality |
| GGUF | i1-IQ3_XS | 19.5 | |
| GGUF | i1-IQ3_S | 20.5 | beats Q3_K* |
| GGUF | i1-Q3_K_S | 20.5 | IQ3_XS probably better |
| GGUF | i1-IQ3_M | 21.5 | |
| GGUF | i1-Q3_K_M | 22.6 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 24.3 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 25.2 | |
| GGUF | i1-Q4_0 | 26.7 | fast, low quality |
| GGUF | i1-Q4_K_S | 26.8 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 28.5 | fast, recommended |
| GGUF | i1-Q4_1 | 29.4 | |
| GGUF | i1-Q5_K_S | 32.3 | |
| GGUF | i1-Q5_K_M | 33.3 | |
| GGUF | i1-Q6_K | 38.5 | 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 sourceVerified Nov 4
Download files
Repository files
File inventory only; completeness is unverified.
- PLLuM-8x7B-chat-2412.i1-IQ1_M.gguf
- PLLuM-8x7B-chat-2412.i1-IQ1_S.gguf
- PLLuM-8x7B-chat-2412.i1-IQ2_M.gguf
- PLLuM-8x7B-chat-2412.i1-IQ2_S.gguf
- PLLuM-8x7B-chat-2412.i1-IQ2_XS.gguf
- PLLuM-8x7B-chat-2412.i1-IQ2_XXS.gguf
- PLLuM-8x7B-chat-2412.i1-IQ3_M.gguf
- PLLuM-8x7B-chat-2412.i1-IQ3_S.gguf
- PLLuM-8x7B-chat-2412.i1-IQ3_XS.gguf
- PLLuM-8x7B-chat-2412.i1-IQ3_XXS.gguf
- PLLuM-8x7B-chat-2412.i1-IQ4_XS.gguf
- PLLuM-8x7B-chat-2412.i1-Q2_K.gguf
- PLLuM-8x7B-chat-2412.i1-Q2_K_S.gguf
- PLLuM-8x7B-chat-2412.i1-Q3_K_L.gguf
- PLLuM-8x7B-chat-2412.i1-Q3_K_M.gguf
- PLLuM-8x7B-chat-2412.i1-Q3_K_S.gguf
- PLLuM-8x7B-chat-2412.i1-Q4_0.gguf
- PLLuM-8x7B-chat-2412.i1-Q4_1.gguf
- PLLuM-8x7B-chat-2412.i1-Q4_K_M.gguf
- PLLuM-8x7B-chat-2412.i1-Q4_K_S.gguf
- PLLuM-8x7B-chat-2412.i1-Q5_K_M.gguf
- PLLuM-8x7B-chat-2412.i1-Q5_K_S.gguf
- PLLuM-8x7B-chat-2412.i1-Q6_K.gguf
- PLLuM-8x7B-chat-2412.imatrix.gguf
Model artifacts
24 artifacts
Model artifacts
24 artifactsPLLuM-8x7B-chat-2412.i1-IQ1_M.gguf
gguf · 10.1 GB · SHA-256 5dba0634c4cc…8e12 · Hugging Face
Download filePLLuM-8x7B-chat-2412.i1-IQ1_S.gguf
gguf · 9.15 GB · SHA-256 7f0d773d6fd3…f357 · Hugging Face
Download filePLLuM-8x7B-chat-2412.i1-IQ2_M.gguf
gguf · 14.4 GB · SHA-256 03575877f189…fe28 · Hugging Face
Download filePLLuM-8x7B-chat-2412.i1-IQ2_S.gguf
gguf · 13.2 GB · SHA-256 7de40672859f…daf2 · Hugging Face
Download filePLLuM-8x7B-chat-2412.i1-IQ2_XS.gguf
gguf · 13.0 GB · SHA-256 da501da0f212…75c5 · Hugging Face
Download filePLLuM-8x7B-chat-2412.i1-IQ2_XXS.gguf
gguf · 11.7 GB · SHA-256 f6e1e7a1cae1…ee50 · Hugging Face
Download filePLLuM-8x7B-chat-2412.i1-IQ3_M.gguf
gguf · 20.0 GB · SHA-256 5369106361bf…4015 · Hugging Face
Download filePLLuM-8x7B-chat-2412.i1-IQ3_S.gguf
gguf · 19.0 GB · SHA-256 af540aa9c309…2d0e · Hugging Face
Download filePLLuM-8x7B-chat-2412.i1-IQ3_XS.gguf
gguf · 18.0 GB · SHA-256 2206be8dedb7…a5af · Hugging Face
Download filePLLuM-8x7B-chat-2412.i1-IQ3_XXS.gguf
gguf · 17.0 GB · SHA-256 1e9a437e4276…cb00 · Hugging Face
Download filePLLuM-8x7B-chat-2412.i1-IQ4_XS.gguf
gguf · 23.4 GB · SHA-256 0ef991041f19…6e79 · Hugging Face
Download filePLLuM-8x7B-chat-2412.i1-Q2_K_S.gguf
gguf · Q2_K_S (unverified) · 14.9 GB · SHA-256 527f18229beb…eee2 · Hugging Face
Download filePLLuM-8x7B-chat-2412.i1-Q2_K.gguf
gguf · Q2_K (unverified) · 16.1 GB · SHA-256 0195a04c0be6…d8fa · Hugging Face
Download filePLLuM-8x7B-chat-2412.i1-Q3_K_L.gguf
gguf · Q3_K_L (unverified) · 22.5 GB · SHA-256 e72542c94ed2…4617 · Hugging Face
Download filePLLuM-8x7B-chat-2412.i1-Q3_K_M.gguf
gguf · Q3_K_M (unverified) · 21.0 GB · SHA-256 2d6b92531246…66be · Hugging Face
Download filePLLuM-8x7B-chat-2412.i1-Q3_K_S.gguf
gguf · Q3_K_S (unverified) · 19.0 GB · SHA-256 05bf42cc0acb…08a6 · Hugging Face
Download filePLLuM-8x7B-chat-2412.i1-Q4_0.gguf
gguf · Q4_0 (unverified) · 24.7 GB · SHA-256 bad24e1c91a5…8c7c · Hugging Face
Download filePLLuM-8x7B-chat-2412.i1-Q4_1.gguf
gguf · Q4_1 (unverified) · 27.3 GB · SHA-256 25265a1a2fc4…be1b · Hugging Face
Download filePLLuM-8x7B-chat-2412.i1-Q4_K_M.gguf
gguf · Q4_K_M (unverified) · 26.5 GB · SHA-256 ccd1b5cde4bd…0a1b · Hugging Face
Download filePLLuM-8x7B-chat-2412.i1-Q4_K_S.gguf
gguf · Q4_K_S (unverified) · 24.9 GB · SHA-256 3365620e6118…79df · Hugging Face
Download filePLLuM-8x7B-chat-2412.i1-Q5_K_M.gguf
gguf · Q5_K_M (unverified) · 30.9 GB · SHA-256 a7fb9e25d4b0…d92d · Hugging Face
Download filePLLuM-8x7B-chat-2412.i1-Q5_K_S.gguf
gguf · Q5_K_S (unverified) · 30.0 GB · SHA-256 30416ba1823b…3a6f · Hugging Face
Download filePLLuM-8x7B-chat-2412.i1-Q6_K.gguf
gguf · Q6_K (unverified) · 35.7 GB · SHA-256 39e262b5dcf3…ed69 · Hugging Face
Download filePLLuM-8x7B-chat-2412.imatrix.gguf
gguf · 24.5 MB · SHA-256 c00b728f6a5f…0827 · Hugging Face
Download fileSource excerpts
3 excerpts
Source excerpts
3 excerpts--- base_model: CYFRAGOVPL/PLLuM-8x7B-chat-2412 language: - pl library_name: transformers license: apache-2.0 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/PLLuM-8x7B-chat-2412 <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#PLLuM-8x7B-chat-2412-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/PLLuM-8x7B-chat-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/PLLuM-8x7B-chat-2412-i1-GGUF/resolve/main/PLLuM-8x7B-chat-2412.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/PLLuM-8x7B-chat-2412-i1-GGUF/resolve/main/PLLuM-8x7B-chat-2412.i1-IQ1_S.gguf) | i1-IQ1_S | 9.9 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/PLLuM-8x7B-chat-2412-i1-GGUF/resolve/main/PLLuM-8x7B-chat-2412.i1-IQ1_M.gguf) | i1-IQ1_M | 10.9 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/PLLuM-8x7B-chat-2412-i1-GGUF/resolve/main/PLLuM-8x7B-chat-2412.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.7 | | | [GGUF](https://huggingface.co/mradermacher/PLLuM-8x7B-chat-2412-i1-GGUF/resolve/main/PLLuM-8x7B-chat-2412.i1-IQ2_XS.gguf) | i1-IQ2_XS | 14.0 | | | [GGUF](https://huggingface.co/mradermacher/PLLuM-8x7B-chat-2412-i1-GGUF/resolve/main/PLLuM-8x7B-chat-2412.i1-IQ2_S.gguf) | i1-IQ2_S | 14.2 | | | [GGUF](https://huggingface.co/mradermacher/PLLuM-8x7B-chat-2412-i1-GGUF/resolve/main/PLLuM-8x7B-chat-2412.i1-IQ2...
Source context: 830 downloads · 0 likes · Library transformers · Repo mradermacher/PLLuM-8x7B-chat-2412-i1-GGUF
Source context: 60 downloads · 0 likes · Library transformers · Repo mradermacher/PLLuM-8x7B-chat-2412-i1-GGUF
