From b19c1655c54e257c3be71ffde434959c956ab4cc Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Tue, 28 Jul 2026 22:37:22 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/Qwen3-VL-8B-Thinking-GGUF Source: Original Platform --- .gitattributes | 49 ++++++++++++++++++ Qwen3-VL-8B-Thinking.IQ4_XS.gguf | 3 ++ Qwen3-VL-8B-Thinking.Q2_K.gguf | 3 ++ Qwen3-VL-8B-Thinking.Q3_K_L.gguf | 3 ++ Qwen3-VL-8B-Thinking.Q3_K_M.gguf | 3 ++ Qwen3-VL-8B-Thinking.Q3_K_S.gguf | 3 ++ Qwen3-VL-8B-Thinking.Q4_K_M.gguf | 3 ++ Qwen3-VL-8B-Thinking.Q4_K_S.gguf | 3 ++ Qwen3-VL-8B-Thinking.Q5_K_M.gguf | 3 ++ Qwen3-VL-8B-Thinking.Q5_K_S.gguf | 3 ++ Qwen3-VL-8B-Thinking.Q6_K.gguf | 3 ++ Qwen3-VL-8B-Thinking.Q8_0.gguf | 3 ++ Qwen3-VL-8B-Thinking.f16.gguf | 3 ++ Qwen3-VL-8B-Thinking.mmproj-Q8_0.gguf | 3 ++ Qwen3-VL-8B-Thinking.mmproj-f16.gguf | 3 ++ README.md | 74 +++++++++++++++++++++++++++ 16 files changed, 165 insertions(+) create mode 100644 .gitattributes create mode 100644 Qwen3-VL-8B-Thinking.IQ4_XS.gguf create mode 100644 Qwen3-VL-8B-Thinking.Q2_K.gguf create mode 100644 Qwen3-VL-8B-Thinking.Q3_K_L.gguf create mode 100644 Qwen3-VL-8B-Thinking.Q3_K_M.gguf create mode 100644 Qwen3-VL-8B-Thinking.Q3_K_S.gguf create mode 100644 Qwen3-VL-8B-Thinking.Q4_K_M.gguf create mode 100644 Qwen3-VL-8B-Thinking.Q4_K_S.gguf create mode 100644 Qwen3-VL-8B-Thinking.Q5_K_M.gguf create mode 100644 Qwen3-VL-8B-Thinking.Q5_K_S.gguf create mode 100644 Qwen3-VL-8B-Thinking.Q6_K.gguf create mode 100644 Qwen3-VL-8B-Thinking.Q8_0.gguf create mode 100644 Qwen3-VL-8B-Thinking.f16.gguf create mode 100644 Qwen3-VL-8B-Thinking.mmproj-Q8_0.gguf create mode 100644 Qwen3-VL-8B-Thinking.mmproj-f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..da3c551 --- /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-8B-Thinking.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VL-8B-Thinking.IQ4_XS.gguf b/Qwen3-VL-8B-Thinking.IQ4_XS.gguf new file mode 100644 index 0000000..01cd86c --- /dev/null +++ b/Qwen3-VL-8B-Thinking.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94b5e143b05730e942c36a145029a4cf079e0c5a28cd69dbcd4c6a5779b0083c +size 4593297952 diff --git a/Qwen3-VL-8B-Thinking.Q2_K.gguf b/Qwen3-VL-8B-Thinking.Q2_K.gguf new file mode 100644 index 0000000..90326a4 --- /dev/null +++ b/Qwen3-VL-8B-Thinking.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cee6415a71c770f436443e9d0b1c87823d4dad6f6aa47a965bd36b6f1e41be92 +size 3281734176 diff --git a/Qwen3-VL-8B-Thinking.Q3_K_L.gguf b/Qwen3-VL-8B-Thinking.Q3_K_L.gguf new file mode 100644 index 0000000..1b26a49 --- /dev/null +++ b/Qwen3-VL-8B-Thinking.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7f3f0fd66cd762e04e5af03599cba7232afe1fadf6356a7ceef879799fce47e +size 4431395360 diff --git a/Qwen3-VL-8B-Thinking.Q3_K_M.gguf b/Qwen3-VL-8B-Thinking.Q3_K_M.gguf new file mode 100644 index 0000000..6b9f0c1 --- /dev/null +++ b/Qwen3-VL-8B-Thinking.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d28432962234546b623a3253f7b6bca27c741b69341cb47e1c7a9b416c8c8e2b +size 4124162592 diff --git a/Qwen3-VL-8B-Thinking.Q3_K_S.gguf b/Qwen3-VL-8B-Thinking.Q3_K_S.gguf new file mode 100644 index 0000000..96d43ff --- /dev/null +++ b/Qwen3-VL-8B-Thinking.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5bae6ee7e22c4c591797a44f78ac127ec5e3c605be9b4030a3a4d0e7eccd14a +size 3769612832 diff --git a/Qwen3-VL-8B-Thinking.Q4_K_M.gguf b/Qwen3-VL-8B-Thinking.Q4_K_M.gguf new file mode 100644 index 0000000..2c445ef --- /dev/null +++ b/Qwen3-VL-8B-Thinking.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e495720e0e823fa8fb9f082a4012ccb412deebc9f03fa83dac7e6e15b477c693 +size 5027785248 diff --git a/Qwen3-VL-8B-Thinking.Q4_K_S.gguf b/Qwen3-VL-8B-Thinking.Q4_K_S.gguf new file mode 100644 index 0000000..85112ce --- /dev/null +++ b/Qwen3-VL-8B-Thinking.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc2bcd609dbea598fe0b084c10575e1bc442d96ba6fe1164dd1a98c1d62bb369 +size 4802013728 diff --git a/Qwen3-VL-8B-Thinking.Q5_K_M.gguf b/Qwen3-VL-8B-Thinking.Q5_K_M.gguf new file mode 100644 index 0000000..efa1402 --- /dev/null +++ b/Qwen3-VL-8B-Thinking.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d7ec74e482abf1d8cf69e8896c99c9cc99a089345f57891d56d2f52eda3dee3 +size 5851114016 diff --git a/Qwen3-VL-8B-Thinking.Q5_K_S.gguf b/Qwen3-VL-8B-Thinking.Q5_K_S.gguf new file mode 100644 index 0000000..a64f7af --- /dev/null +++ b/Qwen3-VL-8B-Thinking.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1080419be1d82546e716a971404d0ab903773d85804b0fb108cf38dbd4238d69 +size 5720762912 diff --git a/Qwen3-VL-8B-Thinking.Q6_K.gguf b/Qwen3-VL-8B-Thinking.Q6_K.gguf new file mode 100644 index 0000000..4cae368 --- /dev/null +++ b/Qwen3-VL-8B-Thinking.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:851d67d34380dee2864bf9cb594ba8944261f4f706da396c6fedd21b84d2ea06 +size 6725900832 diff --git a/Qwen3-VL-8B-Thinking.Q8_0.gguf b/Qwen3-VL-8B-Thinking.Q8_0.gguf new file mode 100644 index 0000000..9797de2 --- /dev/null +++ b/Qwen3-VL-8B-Thinking.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00673fa25542eda8b95d4c01f8f73cf864fe64640fd83bfddd78573eee2d2537 +size 8709519904 diff --git a/Qwen3-VL-8B-Thinking.f16.gguf b/Qwen3-VL-8B-Thinking.f16.gguf new file mode 100644 index 0000000..e066e81 --- /dev/null +++ b/Qwen3-VL-8B-Thinking.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c35f2fb92f7a0310ea127346dcd38f752fad29162f68a6bd039725424d323bfb +size 16388045344 diff --git a/Qwen3-VL-8B-Thinking.mmproj-Q8_0.gguf b/Qwen3-VL-8B-Thinking.mmproj-Q8_0.gguf new file mode 100644 index 0000000..ab9538f --- /dev/null +++ b/Qwen3-VL-8B-Thinking.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09add99dd97f82aa04bd39ec2460e099b9bfb29b7f20e7605346fc85b6dfa87e +size 752289824 diff --git a/Qwen3-VL-8B-Thinking.mmproj-f16.gguf b/Qwen3-VL-8B-Thinking.mmproj-f16.gguf new file mode 100644 index 0000000..667df73 --- /dev/null +++ b/Qwen3-VL-8B-Thinking.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe93f8aeba4c4a141128731b81f3ed13fac5f79dc526f2ea3f0bbe39fb5b4926 +size 1159029920 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b5df739 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: Qwen/Qwen3-VL-8B-Thinking +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Qwen/Qwen3-VL-8B-Thinking + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VL-8B-Thinking-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-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-8B-Thinking-GGUF/resolve/main/Qwen3-VL-8B-Thinking.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-GGUF/resolve/main/Qwen3-VL-8B-Thinking.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-GGUF/resolve/main/Qwen3-VL-8B-Thinking.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-GGUF/resolve/main/Qwen3-VL-8B-Thinking.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-GGUF/resolve/main/Qwen3-VL-8B-Thinking.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-GGUF/resolve/main/Qwen3-VL-8B-Thinking.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-GGUF/resolve/main/Qwen3-VL-8B-Thinking.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-GGUF/resolve/main/Qwen3-VL-8B-Thinking.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-GGUF/resolve/main/Qwen3-VL-8B-Thinking.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-GGUF/resolve/main/Qwen3-VL-8B-Thinking.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-GGUF/resolve/main/Qwen3-VL-8B-Thinking.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-GGUF/resolve/main/Qwen3-VL-8B-Thinking.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-GGUF/resolve/main/Qwen3-VL-8B-Thinking.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-GGUF/resolve/main/Qwen3-VL-8B-Thinking.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. + +