Silver Siren ST 12B I1 GGUF
For a convenient overview and download list, visit our model page for this model.
Modellquelle
- Art
- Other
- Dateigröße
- 6,76 MB–9,37 GB
- Basismodell
- ewald1976/Silver-Siren-ST-12B
- Version
- vRevision e8fcfd1
- Aktualisiert
- 3. Okt. 2026
- Verleger
- @mradermacher
- Downloads
- 1258
- Parameter
- 12B
- Quelle
- Hugging Face
Quellenbeschreibung
About
weighted/imatrix quants of https://huggingface.co/ewald1976/Silver-Siren-ST-12B
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/Silver-Siren-ST-12B-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 | 3.1 | for the desperate |
| GGUF | i1-IQ1_M | 3.3 | mostly desperate |
| GGUF | i1-IQ2_XXS | 3.7 | |
| GGUF | i1-IQ2_XS | 4.0 | |
| GGUF | i1-IQ2_S | 4.2 | |
| GGUF | i1-IQ2_M | 4.5 | |
| GGUF | i1-Q2_K_S | 4.6 | very low quality |
| GGUF | i1-Q2_K | 4.9 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 5.0 | lower quality |
| GGUF | i1-IQ3_XS | 5.4 | |
| GGUF | i1-Q3_K_S | 5.6 | IQ3_XS probably better |
| GGUF | i1-IQ3_S | 5.7 | beats Q3_K* |
| GGUF | i1-IQ3_M | 5.8 | |
| GGUF | i1-Q3_K_M | 6.2 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 6.7 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 6.8 | |
| GGUF | i1-Q4_0 | 7.2 | fast, low quality |
| GGUF | i1-IQ4_NL | 7.2 | prefer IQ4_XS |
| GGUF | i1-Q4_K_S | 7.2 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 7.6 | fast, recommended |
| GGUF | i1-Q4_1 | 7.9 | |
| GGUF | i1-Q5_K_S | 8.6 | |
| GGUF | i1-Q5_K_M | 8.8 | |
| GGUF | i1-Q6_K | 10.2 | 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.
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 3. Okt.
Modellartefakte
25 Artefakte
Modellartefakte
25 ArtefakteSilver-Siren-ST-12B.i1-IQ1_M.gguf
gguf · 3,00 GB · SHA-256 0ddf85a98b4a…3fdc · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-IQ1_S.gguf
gguf · 2,79 GB · SHA-256 1683b6a60cd1…6888 · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-IQ2_M.gguf
gguf · 4,13 GB · SHA-256 c412d824c450…c250 · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-IQ2_S.gguf
gguf · 3,85 GB · SHA-256 6fea6b642009…f2c9 · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-IQ2_XS.gguf
gguf · 3,65 GB · SHA-256 63f37f829f31…04be · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-IQ2_XXS.gguf
gguf · 3,35 GB · SHA-256 de16f335ce94…ba28 · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-IQ3_M.gguf
gguf · 5,33 GB · SHA-256 fe3701ec5af2…9815 · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-IQ3_S.gguf
gguf · 5,18 GB · SHA-256 a1f8066b6ef9…6a04 · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-IQ3_XS.gguf
gguf · 4,94 GB · SHA-256 cf559eb25586…edef · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-IQ3_XXS.gguf
gguf · 4,61 GB · SHA-256 b6e51fe68e4f…c238 · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-IQ4_NL.gguf
gguf · 6,61 GB · SHA-256 f15535c8e070…0b82 · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-IQ4_XS.gguf
gguf · 6,28 GB · SHA-256 fa1303bfb74a…0edf · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-Q2_K_S.gguf
gguf · 4,19 GB · SHA-256 7514f58c9030…0e6a · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-Q2_K.gguf
gguf · 4,46 GB · SHA-256 9a4104e6d822…7c98 · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-Q3_K_L.gguf
gguf · 6,11 GB · SHA-256 9b37c88baf97…8164 · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-Q3_K_M.gguf
gguf · 5,67 GB · SHA-256 06cc12186507…39f6 · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-Q3_K_S.gguf
gguf · 5,15 GB · SHA-256 174dcaaa487f…1f74 · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-Q4_0.gguf
gguf · 6,61 GB · SHA-256 bd69b6509562…7e70 · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-Q4_1.gguf
gguf · 7,26 GB · SHA-256 bc931e265734…66e0 · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-Q4_K_M.gguf
gguf · 6,96 GB · SHA-256 dd46d5e100cb…a7cf · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-Q4_K_S.gguf
gguf · 6,63 GB · SHA-256 60ff222c433c…25db · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-Q5_K_M.gguf
gguf · 8,13 GB · SHA-256 e8cf446fc0f1…20b0 · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-Q5_K_S.gguf
gguf · 7,93 GB · SHA-256 ab18625227be…f819 · Hugging Face
HerunterladenSilver-Siren-ST-12B.i1-Q6_K.gguf
gguf · 9,37 GB · SHA-256 fc36013023dd…43d9 · Hugging Face
HerunterladenSilver-Siren-ST-12B.imatrix.gguf
gguf · 6,76 MB · SHA-256 b4cff168439f…6ff3 · Hugging Face
HerunterladenQuellenauszüge
3 Auszüge
Quellenauszüge
3 Auszüge--- base_model: ewald1976/Silver-Siren-ST-12B datasets: - ewald1976/opus48-gpt55-asimov.jsonl language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - mistral - sft - unsloth - style-tune - roleplay - creative - 12b - nemo --- ## 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/ewald1976/Silver-Siren-ST-12B <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Silver-Siren-ST-12B-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/Silver-Siren-ST-12B-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/Silver-Siren-ST-12B-i1-GGUF/resolve/main/Silver-Siren-ST-12B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/Silver-Siren-ST-12B-i1-GGUF/resolve/main/Silver-Siren-ST-12B.i1-IQ1_S.gguf) | i1-IQ1_S | 3.1 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Silver-Siren-ST-12B-i1-GGUF/resolve/main/Silver-Siren-ST-12B.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/Silver-Siren-ST-12B-i1-GGUF/resolve/main/Silver-Siren-ST-12B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 | | | [GGUF](https://huggingface.co/mradermacher/Silver-Siren-ST-12B-i1-GGUF/resolve/main/Silver-Siren-ST-12B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | | | [GGUF](https://huggingface.co/mradermacher/Silver-Siren-ST-12B-i1-GGUF/resolve/main/Silver-Siren-ST-12B.i1-IQ2_S.gguf) | i1-IQ2_S | 4.2 | | | [GGUF]...
Source context: 1258 downloads · 4 likes · Library transformers · Repo mradermacher/Silver-Siren-ST-12B-i1-GGUF
Source context: 1183 downloads · 3 likes · Library transformers · Repo mradermacher/Silver-Siren-ST-12B-i1-GGUF
