commit 9addd3e726b7a090bdd1132cc4628d89218caa92 Author: ModelHub XC Date: Thu Jul 30 11:53:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-VL-Reranker-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2c1ece1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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-Reranker-8B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VL-Reranker-8B.IQ4_XS.gguf b/Qwen3-VL-Reranker-8B.IQ4_XS.gguf new file mode 100644 index 0000000..65f257a --- /dev/null +++ b/Qwen3-VL-Reranker-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:101ea05147a2ec4da3aef38c50f3a9dbd1a0a923c551ebe035cdbcc5c2696f75 +size 4593298400 diff --git a/Qwen3-VL-Reranker-8B.Q2_K.gguf b/Qwen3-VL-Reranker-8B.Q2_K.gguf new file mode 100644 index 0000000..502103b --- /dev/null +++ b/Qwen3-VL-Reranker-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc4f7f471a8fb4c02f2b246e050dbc143a485e9fb54427be1206f160cdba6067 +size 3281734624 diff --git a/Qwen3-VL-Reranker-8B.Q3_K_L.gguf b/Qwen3-VL-Reranker-8B.Q3_K_L.gguf new file mode 100644 index 0000000..aecedb7 --- /dev/null +++ b/Qwen3-VL-Reranker-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d7780371d39fffa7c7b28d3fd3f9842f94806fc1a67729f655621706970c280 +size 4431395808 diff --git a/Qwen3-VL-Reranker-8B.Q3_K_M.gguf b/Qwen3-VL-Reranker-8B.Q3_K_M.gguf new file mode 100644 index 0000000..1cb6421 --- /dev/null +++ b/Qwen3-VL-Reranker-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d43af8db8db03547e15112cdbbae5c3c9543315394fa868f80c0bdc73de87bc5 +size 4124163040 diff --git a/Qwen3-VL-Reranker-8B.Q3_K_S.gguf b/Qwen3-VL-Reranker-8B.Q3_K_S.gguf new file mode 100644 index 0000000..f50a49a --- /dev/null +++ b/Qwen3-VL-Reranker-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:656f33192c18a0cb6da7e731a49d487fc5ac89bd8b523086fc2db12a99c28095 +size 3769613280 diff --git a/Qwen3-VL-Reranker-8B.Q4_K_M.gguf b/Qwen3-VL-Reranker-8B.Q4_K_M.gguf new file mode 100644 index 0000000..2048e2a --- /dev/null +++ b/Qwen3-VL-Reranker-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f73e62ea68abf741c3e713af823cfb4d2fd2ca35c8b68277b87b4b3d8570b66d +size 5027785696 diff --git a/Qwen3-VL-Reranker-8B.Q4_K_S.gguf b/Qwen3-VL-Reranker-8B.Q4_K_S.gguf new file mode 100644 index 0000000..db6c3d0 --- /dev/null +++ b/Qwen3-VL-Reranker-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbfba438a135ff8a612fc0f46ee9c65b0d5a1b0eb57ced2a4c10744b1590ae37 +size 4802014176 diff --git a/Qwen3-VL-Reranker-8B.Q5_K_M.gguf b/Qwen3-VL-Reranker-8B.Q5_K_M.gguf new file mode 100644 index 0000000..05020f0 --- /dev/null +++ b/Qwen3-VL-Reranker-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dcc6b7e9843319cd23ea996a765b5146b73300305aba58c7eed3d5affab2583 +size 5851114464 diff --git a/Qwen3-VL-Reranker-8B.Q5_K_S.gguf b/Qwen3-VL-Reranker-8B.Q5_K_S.gguf new file mode 100644 index 0000000..244b400 --- /dev/null +++ b/Qwen3-VL-Reranker-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dbc7a43b45d4f227333395b3c046c928e6a246ce48db537ed1a7db923746dd8 +size 5720763360 diff --git a/Qwen3-VL-Reranker-8B.Q6_K.gguf b/Qwen3-VL-Reranker-8B.Q6_K.gguf new file mode 100644 index 0000000..1c0a542 --- /dev/null +++ b/Qwen3-VL-Reranker-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c40c98b602cbdda4cd72bf3b59c0065522ea30458888d31b0236ed9a3f431b7 +size 6725901280 diff --git a/Qwen3-VL-Reranker-8B.Q8_0.gguf b/Qwen3-VL-Reranker-8B.Q8_0.gguf new file mode 100644 index 0000000..d303dc4 --- /dev/null +++ b/Qwen3-VL-Reranker-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:275e1f566cdc3355ce99d1b9a764737b7829b06566f356d9a6b5fdcf701c2779 +size 8709520352 diff --git a/Qwen3-VL-Reranker-8B.f16.gguf b/Qwen3-VL-Reranker-8B.f16.gguf new file mode 100644 index 0000000..4a609f1 --- /dev/null +++ b/Qwen3-VL-Reranker-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fff1a41d308bc3e67cf08cceb06c7d4dfdcae676e5b88d8a5b7d3d3afc219c0 +size 16388045792 diff --git a/Qwen3-VL-Reranker-8B.mmproj-Q8_0.gguf b/Qwen3-VL-Reranker-8B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..1a7692e --- /dev/null +++ b/Qwen3-VL-Reranker-8B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a83c759ef7009ddd7cb761512a2454c5d6d5383e46b6ed83719b04a04b331e19 +size 752290240 diff --git a/Qwen3-VL-Reranker-8B.mmproj-f16.gguf b/Qwen3-VL-Reranker-8B.mmproj-f16.gguf new file mode 100644 index 0000000..bf969f4 --- /dev/null +++ b/Qwen3-VL-Reranker-8B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15cd9bd4882dae771344f0ac204fce07de91b47c1438ada3861dfc817403c31e +size 1159030336 diff --git a/README.md b/README.md new file mode 100644 index 0000000..450073e --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: Qwen/Qwen3-VL-Reranker-8B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- sentence-transformers +- transformers +- multimodal rerank +- text rerank +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Qwen/Qwen3-VL-Reranker-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VL-Reranker-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-VL-Reranker-8B-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-Reranker-8B-GGUF/resolve/main/Qwen3-VL-Reranker-8B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-8B-GGUF/resolve/main/Qwen3-VL-Reranker-8B.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-8B-GGUF/resolve/main/Qwen3-VL-Reranker-8B.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-8B-GGUF/resolve/main/Qwen3-VL-Reranker-8B.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-8B-GGUF/resolve/main/Qwen3-VL-Reranker-8B.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-8B-GGUF/resolve/main/Qwen3-VL-Reranker-8B.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-8B-GGUF/resolve/main/Qwen3-VL-Reranker-8B.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-8B-GGUF/resolve/main/Qwen3-VL-Reranker-8B.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-8B-GGUF/resolve/main/Qwen3-VL-Reranker-8B.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-8B-GGUF/resolve/main/Qwen3-VL-Reranker-8B.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-8B-GGUF/resolve/main/Qwen3-VL-Reranker-8B.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-8B-GGUF/resolve/main/Qwen3-VL-Reranker-8B.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-8B-GGUF/resolve/main/Qwen3-VL-Reranker-8B.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-8B-GGUF/resolve/main/Qwen3-VL-Reranker-8B.f16.gguf) | f16 | 16.5 | 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. + +