Qwen3 VL Embedding 8B I1 GGUF
For a convenient overview and download list, visit our model page for this model.
Modellquelle
- Art
- Embedding
- Dateigröße
- 5,10 MB–5,79 GB
- Basismodell
- Qwen/Qwen3-VL-Embedding-8B
- Version
- vRevision fa8fcd8
- Aktualisiert
- 3. Okt. 2026
- Verleger
- @mradermacher
- Downloads
- 1937
- Parameter
- 8B
- Quelle
- Hugging Face
Quellenbeschreibung
About
weighted/imatrix quants of https://huggingface.co/Qwen/Qwen3-VL-Embedding-8B
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/Qwen3-VL-Embedding-8B-GGUF
This is a vision model - mmproj files (if any) will be in the static repository.
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 | 2.0 | for the desperate |
| GGUF | i1-IQ1_M | 2.2 | mostly desperate |
| GGUF | i1-IQ2_XXS | 2.4 | |
| GGUF | i1-IQ2_XS | 2.6 | |
| GGUF | i1-IQ2_S | 2.7 | |
| GGUF | i1-IQ2_M | 2.9 | |
| GGUF | i1-Q2_K_S | 3.0 | very low quality |
| GGUF | i1-Q2_K | 3.2 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 3.2 | lower quality |
| GGUF | i1-IQ3_XS | 3.5 | |
| GGUF | i1-Q3_K_S | 3.6 | IQ3_XS probably better |
| GGUF | i1-IQ3_S | 3.6 | beats Q3_K* |
| GGUF | i1-IQ3_M | 3.7 | |
| GGUF | i1-Q3_K_M | 4.0 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 4.3 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 4.3 | |
| GGUF | i1-Q4_0 | 4.5 | fast, low quality |
| GGUF | i1-IQ4_NL | 4.5 | prefer IQ4_XS |
| GGUF | i1-Q4_K_S | 4.6 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 4.8 | fast, recommended |
| GGUF | i1-Q4_1 | 5.0 | |
| GGUF | i1-Q5_K_S | 5.4 | |
| GGUF | i1-Q5_K_M | 5.5 | |
| GGUF | i1-Q6_K | 6.3 | 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 ArtefakteQwen3-VL-Embedding-8B.i1-IQ1_M.gguf
gguf · 1,91 GB · SHA-256 5c775d74662c…ec71 · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-IQ1_S.gguf
gguf · 1,78 GB · SHA-256 d81f46ac6afd…5b3a · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-IQ2_M.gguf
gguf · 2,59 GB · SHA-256 dd471b43023e…1c86 · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-IQ2_S.gguf
gguf · 2,42 GB · SHA-256 db38052c64fb…1b96 · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-IQ2_XS.gguf
gguf · 2,32 GB · SHA-256 dc16283b6d5c…752d · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-IQ2_XXS.gguf
gguf · 2,13 GB · SHA-256 28a58c1681df…26b2 · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-IQ3_M.gguf
gguf · 3,38 GB · SHA-256 27871157b405…638f · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-IQ3_S.gguf
gguf · 3,28 GB · SHA-256 e2a8c4184ec2…73aa · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-IQ3_XS.gguf
gguf · 3,13 GB · SHA-256 c01229d924fa…e7bc · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-IQ3_XXS.gguf
gguf · 2,89 GB · SHA-256 c8fc05dcc977…a5ad · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-IQ4_NL.gguf
gguf · 4,14 GB · SHA-256 607468f613f9…a0e0 · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-IQ4_XS.gguf
gguf · 3,94 GB · SHA-256 7254a5068a57…cebf · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-Q2_K_S.gguf
gguf · 2,68 GB · SHA-256 39c8b1315d17…5b39 · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-Q2_K.gguf
gguf · 2,87 GB · SHA-256 8638a22c38df…9ed0 · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-Q3_K_L.gguf
gguf · 3,88 GB · SHA-256 e5142c7cb1ba…7733 · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-Q3_K_M.gguf
gguf · 3,59 GB · SHA-256 4c9f2e9c91fc…32e0 · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-Q3_K_S.gguf
gguf · 3,26 GB · SHA-256 e3e7d4b03905…0da2 · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-Q4_0.gguf
gguf · 4,13 GB · SHA-256 8521e139698a…3bfd · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-Q4_1.gguf
gguf · 4,53 GB · SHA-256 b8622f619f3c…f608 · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-Q4_K_M.gguf
gguf · 4,36 GB · SHA-256 700237baebef…bf80 · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-Q4_K_S.gguf
gguf · 4,15 GB · SHA-256 09c0307d558d…bae3 · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-Q5_K_M.gguf
gguf · 5,05 GB · SHA-256 2759e7cb2989…da13 · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-Q5_K_S.gguf
gguf · 4,93 GB · SHA-256 0ab0592ecd8b…250c · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.i1-Q6_K.gguf
gguf · 5,79 GB · SHA-256 045b44266b19…6e92 · Hugging Face
HerunterladenQwen3-VL-Embedding-8B.imatrix.gguf
gguf · 5,10 MB · SHA-256 5bff63770180…a833 · Hugging Face
HerunterladenQuellenauszüge
3 Auszüge
Quellenauszüge
3 Auszüge--- base_model: Qwen/Qwen3-VL-Embedding-8B language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - sentence-transformers - transformers - multimodal embedding - qwen - embedding --- ## 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/Qwen/Qwen3-VL-Embedding-8B <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VL-Embedding-8B-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/Qwen3-VL-Embedding-8B-GGUF **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Qwen3-VL-Embedding-8B-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/Qwen3-VL-Embedding-8B-i1-GGUF/resolve/main/Qwen3-VL-Embedding-8B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Embedding-8B-i1-GGUF/resolve/main/Qwen3-VL-Embedding-8B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Embedding-8B-i1-GGUF/resolve/main/Qwen3-VL-Embedding-8B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.2 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Embedding-8B-i1-GGUF/resolve/main/Qwen3-VL-Embedding-8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | | [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Embedding-8B-i1-GGUF/resolve/main/Qwen3-VL-Embedding-8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | | [GGUF](https://hugg...
Source context: 1937 downloads · 1 likes · Library transformers · Repo mradermacher/Qwen3-VL-Embedding-8B-i1-GGUF
Source context: 747 downloads · 0 likes · Library transformers · Repo mradermacher/Qwen3-VL-Embedding-8B-i1-GGUF
