commit 7c17968375ea373ce76f04d581afa783c6fcd018 Author: ModelHub XC Date: Wed Sep 16 13:54:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-VL-Embedding-2B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..57a3d19 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Embedding-2B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Embedding-2B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Embedding-2B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Embedding-2B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Embedding-2B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Embedding-2B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Embedding-2B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Embedding-2B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Embedding-2B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Embedding-2B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Embedding-2B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Embedding-2B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Embedding-2B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Embedding-2B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VL-Embedding-2B.IQ4_XS.gguf b/Qwen3-VL-Embedding-2B.IQ4_XS.gguf new file mode 100644 index 0000000..d481628 --- /dev/null +++ b/Qwen3-VL-Embedding-2B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a00cbabcf30b612ef788e6a0fc80e2e35830ee85ab72d916aa62a84375d339ef +size 1016283296 diff --git a/Qwen3-VL-Embedding-2B.Q2_K.gguf b/Qwen3-VL-Embedding-2B.Q2_K.gguf new file mode 100644 index 0000000..250ae35 --- /dev/null +++ b/Qwen3-VL-Embedding-2B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e00d608e664f833415e1ede35e19ec007b53165d6ee548a35621ba0df5170479 +size 777797792 diff --git a/Qwen3-VL-Embedding-2B.Q3_K_L.gguf b/Qwen3-VL-Embedding-2B.Q3_K_L.gguf new file mode 100644 index 0000000..bd50449 --- /dev/null +++ b/Qwen3-VL-Embedding-2B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbb3c9c07724cd39a371c75e1ddd30b8ff6d745e38c7624024035217c283aa27 +size 1003503776 diff --git a/Qwen3-VL-Embedding-2B.Q3_K_M.gguf b/Qwen3-VL-Embedding-2B.Q3_K_M.gguf new file mode 100644 index 0000000..410ae9b --- /dev/null +++ b/Qwen3-VL-Embedding-2B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01fc38837f9da4e0563a8aa3fa65e1032fcfd9bb9c37de87a3e05ecceb2c509a +size 939540640 diff --git a/Qwen3-VL-Embedding-2B.Q3_K_S.gguf b/Qwen3-VL-Embedding-2B.Q3_K_S.gguf new file mode 100644 index 0000000..106dca9 --- /dev/null +++ b/Qwen3-VL-Embedding-2B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf23a8f3f00c14d37be4b49506a2fa0420cdaec52d38ee9c20c3d3829e459898 +size 867254432 diff --git a/Qwen3-VL-Embedding-2B.Q4_K_M.gguf b/Qwen3-VL-Embedding-2B.Q4_K_M.gguf new file mode 100644 index 0000000..43b7d61 --- /dev/null +++ b/Qwen3-VL-Embedding-2B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7812c91cd1e03ab4d42fdc21264b9f9d116f8b57b350ac186bd9ec07546984da +size 1107411104 diff --git a/Qwen3-VL-Embedding-2B.Q4_K_S.gguf b/Qwen3-VL-Embedding-2B.Q4_K_S.gguf new file mode 100644 index 0000000..ada1586 --- /dev/null +++ b/Qwen3-VL-Embedding-2B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6391b62685b47fa6b6f2841395b940673c77a151bd76382e0ff0c75ac35f32c0 +size 1060192416 diff --git a/Qwen3-VL-Embedding-2B.Q5_K_M.gguf b/Qwen3-VL-Embedding-2B.Q5_K_M.gguf new file mode 100644 index 0000000..8b86ddf --- /dev/null +++ b/Qwen3-VL-Embedding-2B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:611caf4e6cc7ab69249ecb2a72120dc8a1c023a21cc86c96bff57cc790b029c8 +size 1257881760 diff --git a/Qwen3-VL-Embedding-2B.Q5_K_S.gguf b/Qwen3-VL-Embedding-2B.Q5_K_S.gguf new file mode 100644 index 0000000..aa5275f --- /dev/null +++ b/Qwen3-VL-Embedding-2B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:165820159ce38a6c11fe52d0c2262a90b5b919da9e2a5745bb055ef280879e71 +size 1230586016 diff --git a/Qwen3-VL-Embedding-2B.Q6_K.gguf b/Qwen3-VL-Embedding-2B.Q6_K.gguf new file mode 100644 index 0000000..c4e82bc --- /dev/null +++ b/Qwen3-VL-Embedding-2B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25b5a6cbdfc28f3d22a1240892ef2020f527eeb79a6c45ce8127a44ec4cc5e38 +size 1417756832 diff --git a/Qwen3-VL-Embedding-2B.Q8_0.gguf b/Qwen3-VL-Embedding-2B.Q8_0.gguf new file mode 100644 index 0000000..c8374dd --- /dev/null +++ b/Qwen3-VL-Embedding-2B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26fadde153b2266d244de4752c2dcba35be78872bdeeb005390b74689d45d851 +size 1834428576 diff --git a/Qwen3-VL-Embedding-2B.f16.gguf b/Qwen3-VL-Embedding-2B.f16.gguf new file mode 100644 index 0000000..8a358cc --- /dev/null +++ b/Qwen3-VL-Embedding-2B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cc6837215658d94340f0965724d0653f2660eb27a25ac2786bbe09c54cf9002 +size 3447351456 diff --git a/Qwen3-VL-Embedding-2B.mmproj-Q8_0.gguf b/Qwen3-VL-Embedding-2B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..b7b9664 --- /dev/null +++ b/Qwen3-VL-Embedding-2B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa5a22b400fcfa32453656fdc7063bd2c80007030a79cb4f07f7c19cb1e40e8e +size 445053568 diff --git a/Qwen3-VL-Embedding-2B.mmproj-f16.gguf b/Qwen3-VL-Embedding-2B.mmproj-f16.gguf new file mode 100644 index 0000000..2e63016 --- /dev/null +++ b/Qwen3-VL-Embedding-2B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:521c481325245b7cb043fd33cfd891abf31c1925f504235fb8ca9d6b1dd5eb9d +size 819395200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..48d7cd8 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: Qwen/Qwen3-VL-Embedding-2B +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 + + + + + + + + + +static quants of https://huggingface.co/Qwen/Qwen3-VL-Embedding-2B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VL-Embedding-2B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-VL-Embedding-2B-i1-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-2B-GGUF/resolve/main/Qwen3-VL-Embedding-2B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Embedding-2B-GGUF/resolve/main/Qwen3-VL-Embedding-2B.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Embedding-2B-GGUF/resolve/main/Qwen3-VL-Embedding-2B.mmproj-f16.gguf) | mmproj-f16 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Embedding-2B-GGUF/resolve/main/Qwen3-VL-Embedding-2B.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Embedding-2B-GGUF/resolve/main/Qwen3-VL-Embedding-2B.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Embedding-2B-GGUF/resolve/main/Qwen3-VL-Embedding-2B.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Embedding-2B-GGUF/resolve/main/Qwen3-VL-Embedding-2B.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Embedding-2B-GGUF/resolve/main/Qwen3-VL-Embedding-2B.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Embedding-2B-GGUF/resolve/main/Qwen3-VL-Embedding-2B.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Embedding-2B-GGUF/resolve/main/Qwen3-VL-Embedding-2B.Q5_K_S.gguf) | Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Embedding-2B-GGUF/resolve/main/Qwen3-VL-Embedding-2B.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Embedding-2B-GGUF/resolve/main/Qwen3-VL-Embedding-2B.Q6_K.gguf) | Q6_K | 1.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Embedding-2B-GGUF/resolve/main/Qwen3-VL-Embedding-2B.Q8_0.gguf) | Q8_0 | 1.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Embedding-2B-GGUF/resolve/main/Qwen3-VL-Embedding-2B.f16.gguf) | f16 | 3.5 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.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](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +