Du hast einen ComfyUI-Workflow? Erstelle direkt im Browser eine verständliche Workflow-Dokumentation.Workflow verständlich machen.Jetzt ausprobieren ↗
For a convenient overview and download list, visit our model page for this model.
Modellquelle
Quellenbeschreibung
weighted/imatrix quants of https://huggingface.co/aifeifei798/Darkidol-Gemma-4-E2B-it
For a convenient overview and download list, visit our model page for this model.
static quants are available at
Quellen
1 QuelleVerifiziert 26. Sept.
Modellartefakte
16 ArtefakteDarkidol-Gemma-4-E2B-it.i1-IQ3_M.gguf
gguf · 2,92 GB · SHA-256 c37bafb3528f…a841 · Hugging Face
HerunterladenDarkidol-Gemma-4-E2B-it.i1-IQ3_S.gguf
gguf · 2,90 GB · SHA-256 484464a81bfc…6fcd · Hugging Face
HerunterladenQuellenauszüge
2 AuszügeThis is a vision model - mmproj files (if any) will be in the static repository.
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.
(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-Q2_K | 3.1 | IQ3_XXS probably better |
| GGUF | i1-Q3_K_S | 3.2 | IQ3_XS probably better |
| GGUF | i1-IQ3_S | 3.2 | beats Q3_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
See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.
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.
Darkidol-Gemma-4-E2B-it.i1-IQ4_NL.gguf
gguf · 3,13 GB · SHA-256 6d5889d1f173…2c06 · Hugging Face
HerunterladenDarkidol-Gemma-4-E2B-it.i1-IQ4_XS.gguf
gguf · 3,08 GB · SHA-256 1a215f5f0e1d…6a54 · Hugging Face
HerunterladenDarkidol-Gemma-4-E2B-it.i1-Q2_K.gguf
gguf · 2,78 GB · SHA-256 7fc2125475b1…07db · Hugging Face
HerunterladenDarkidol-Gemma-4-E2B-it.i1-Q3_K_L.gguf
gguf · 3,06 GB · SHA-256 47dcf4b0d15a…5062 · Hugging Face
HerunterladenDarkidol-Gemma-4-E2B-it.i1-Q3_K_M.gguf
gguf · 2,98 GB · SHA-256 23fe96d0d15c…6d28 · Hugging Face
HerunterladenDarkidol-Gemma-4-E2B-it.i1-Q3_K_S.gguf
gguf · 2,90 GB · SHA-256 8e8e20eba338…85fb · Hugging Face
HerunterladenDarkidol-Gemma-4-E2B-it.i1-Q4_0.gguf
gguf · 3,13 GB · SHA-256 d0b32d5eef86…efa3 · Hugging Face
HerunterladenDarkidol-Gemma-4-E2B-it.i1-Q4_1.gguf
gguf · 3,24 GB · SHA-256 0125ef1d5e79…9808 · Hugging Face
HerunterladenDarkidol-Gemma-4-E2B-it.i1-Q4_K_M.gguf
gguf · 3,19 GB · SHA-256 c72ddc2d3a55…938e · Hugging Face
HerunterladenDarkidol-Gemma-4-E2B-it.i1-Q4_K_S.gguf
gguf · 3,13 GB · SHA-256 23d616c03427…33bf · Hugging Face
HerunterladenDarkidol-Gemma-4-E2B-it.i1-Q5_K_M.gguf
gguf · 3,38 GB · SHA-256 e30557731ea6…118e · Hugging Face
HerunterladenDarkidol-Gemma-4-E2B-it.i1-Q5_K_S.gguf
gguf · 3,35 GB · SHA-256 0368ef4fd95e…b409 · Hugging Face
HerunterladenDarkidol-Gemma-4-E2B-it.i1-Q6_K.gguf
gguf · 3,58 GB · SHA-256 c14629adf53e…a5de · Hugging Face
HerunterladenDarkidol-Gemma-4-E2B-it.imatrix.gguf
gguf · 2,69 MB · SHA-256 4f23706e741c…3912 · Hugging Face
Herunterladen--- base_model: aifeifei798/Darkidol-Gemma-4-E2B-it language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - roleplay - gemma - gemma4 - sillytavern - idol - pytorch - DarkIdol - Queen - any-to-any - OpenClaw --- ## 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/aifeifei798/Darkidol-Gemma-4-E2B-it <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Darkidol-Gemma-4-E2B-it-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/Darkidol-Gemma-4-E2B-it-GGUF **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Darkidol-Gemma-4-E2B-it-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/Darkidol-Gemma-4-E2B-it-i1-GGUF/resolve/main/Darkidol-Gemma-4-E2B-it.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/Darkidol-Gemma-4-E2B-it-i1-GGUF/resolve/main/Darkidol-Gemma-4-E2B-it.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better | | [GGUF](https://huggingface.co/mradermacher/Darkidol-Gemma-4-E2B-it-i1-GGUF/resolve/main/Darkidol-Gemma-4-E2B-it.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.2 | IQ3_XS probably better | | [GGUF](https://huggingface.co/mradermacher/Darkidol-Gemma-4-E2B-it-i1-GGUF/resolve/main/Darkidol-Gemma-4-E2B-it.i1-IQ3_S.gguf) | i1-IQ3_S | 3.2 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Darkidol-Gemma-4-E2B-it-i1-GGUF/resolve/mai...
Source context: 732 downloads · 2 likes · Pipeline any-to-any · Library transformers · Repo mradermacher/Darkidol-Gemma-4-E2B-it-i1-GGUF
| GGUF | i1-IQ3_M | 3.2 |
| GGUF | i1-Q3_K_M | 3.3 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 3.4 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 3.4 |
| GGUF | i1-IQ4_NL | 3.5 | prefer IQ4_XS |
| GGUF | i1-Q4_0 | 3.5 | fast, low quality |
| GGUF | i1-Q4_K_S | 3.5 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 3.5 | fast, recommended |
| GGUF | i1-Q4_1 | 3.6 |
| GGUF | i1-Q5_K_S | 3.7 |
| GGUF | i1-Q5_K_M | 3.7 |
| GGUF | i1-Q6_K | 3.9 | practically like static Q6_K |
