commit 7857faf289fbdd7a6eeaf808abf7414cfdfac42b Author: ModelHub XC Date: Sun Jul 19 00:54:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-VL-8B-Thinking-norm-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..08b9135 --- /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-8B-Thinking-norm.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking-norm.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking-norm.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking-norm.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking-norm.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking-norm.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking-norm.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking-norm.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking-norm.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking-norm.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking-norm.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking-norm.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Thinking-norm.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VL-8B-Thinking-norm.IQ4_XS.gguf b/Qwen3-VL-8B-Thinking-norm.IQ4_XS.gguf new file mode 100644 index 0000000..de53829 --- /dev/null +++ b/Qwen3-VL-8B-Thinking-norm.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85d3cf5e22486b21432ce875a30d638b965b647a0d997300e4459fb29e32a645 +size 4593298912 diff --git a/Qwen3-VL-8B-Thinking-norm.Q2_K.gguf b/Qwen3-VL-8B-Thinking-norm.Q2_K.gguf new file mode 100644 index 0000000..8a921fb --- /dev/null +++ b/Qwen3-VL-8B-Thinking-norm.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c82346a50b03ba16bcb80edf57fac1a3a36767f4417448014530e782ddc19ff8 +size 3281735136 diff --git a/Qwen3-VL-8B-Thinking-norm.Q3_K_L.gguf b/Qwen3-VL-8B-Thinking-norm.Q3_K_L.gguf new file mode 100644 index 0000000..3790622 --- /dev/null +++ b/Qwen3-VL-8B-Thinking-norm.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2856852ee97956c5a0d2e58e46d1b0ab3d756500b65624c92538c2f32e7a829 +size 4431396320 diff --git a/Qwen3-VL-8B-Thinking-norm.Q3_K_M.gguf b/Qwen3-VL-8B-Thinking-norm.Q3_K_M.gguf new file mode 100644 index 0000000..d8fb319 --- /dev/null +++ b/Qwen3-VL-8B-Thinking-norm.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8a1016a6c89dc5393cf628b5e02ac951400afb682eb8d2b445f1468a287eca6 +size 4124163552 diff --git a/Qwen3-VL-8B-Thinking-norm.Q3_K_S.gguf b/Qwen3-VL-8B-Thinking-norm.Q3_K_S.gguf new file mode 100644 index 0000000..fb4f71a --- /dev/null +++ b/Qwen3-VL-8B-Thinking-norm.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bde78b4458812c3a6c91a9a7a8ad4c4339d9864cd31e7105ccda9156ade22c3d +size 3769613792 diff --git a/Qwen3-VL-8B-Thinking-norm.Q4_K_M.gguf b/Qwen3-VL-8B-Thinking-norm.Q4_K_M.gguf new file mode 100644 index 0000000..4d6a4c0 --- /dev/null +++ b/Qwen3-VL-8B-Thinking-norm.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23aed3b9847babdafcadb95f3ef43da21bdbae57253914c14dad27787e0e2225 +size 5027786208 diff --git a/Qwen3-VL-8B-Thinking-norm.Q4_K_S.gguf b/Qwen3-VL-8B-Thinking-norm.Q4_K_S.gguf new file mode 100644 index 0000000..05e25a3 --- /dev/null +++ b/Qwen3-VL-8B-Thinking-norm.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f3c94ac6167b2ff6f0097fcd523829dc5dcb2c92653fa366c48b5fde1342c7b +size 4802014688 diff --git a/Qwen3-VL-8B-Thinking-norm.Q5_K_M.gguf b/Qwen3-VL-8B-Thinking-norm.Q5_K_M.gguf new file mode 100644 index 0000000..17cced4 --- /dev/null +++ b/Qwen3-VL-8B-Thinking-norm.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f75c35d3961830de0b0bc95094d360b3e8a2a5887b6eb6e97e6e9a5491588c28 +size 5851114976 diff --git a/Qwen3-VL-8B-Thinking-norm.Q5_K_S.gguf b/Qwen3-VL-8B-Thinking-norm.Q5_K_S.gguf new file mode 100644 index 0000000..12c2d68 --- /dev/null +++ b/Qwen3-VL-8B-Thinking-norm.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b342284118ca8d6af32b7d7ef33b068b35551effa0c82d3275e3a44d0813a827 +size 5720763872 diff --git a/Qwen3-VL-8B-Thinking-norm.Q6_K.gguf b/Qwen3-VL-8B-Thinking-norm.Q6_K.gguf new file mode 100644 index 0000000..f39220e --- /dev/null +++ b/Qwen3-VL-8B-Thinking-norm.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc6cba2a4d7687070fcb48412e414b00566efcad48259bbaf435157f01e34aec +size 6725901792 diff --git a/Qwen3-VL-8B-Thinking-norm.Q8_0.gguf b/Qwen3-VL-8B-Thinking-norm.Q8_0.gguf new file mode 100644 index 0000000..e1edfd4 --- /dev/null +++ b/Qwen3-VL-8B-Thinking-norm.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6fda3394e1af5e1a1d87d0b3294bae0257d041518c05a178a2d0819d495833e +size 8709520864 diff --git a/Qwen3-VL-8B-Thinking-norm.f16.gguf b/Qwen3-VL-8B-Thinking-norm.f16.gguf new file mode 100644 index 0000000..1cffcad --- /dev/null +++ b/Qwen3-VL-8B-Thinking-norm.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecbbc2a095333177710ee0b7eafd75ee1dca42bc79f9cc1ab9438cf015dbef7a +size 16388046304 diff --git a/Qwen3-VL-8B-Thinking-norm.mmproj-Q8_0.gguf b/Qwen3-VL-8B-Thinking-norm.mmproj-Q8_0.gguf new file mode 100644 index 0000000..9e2a3a7 --- /dev/null +++ b/Qwen3-VL-8B-Thinking-norm.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e16eb15674e42aa014d1c14dee22640250695882e7afe3d170667f2633b727f +size 752290240 diff --git a/Qwen3-VL-8B-Thinking-norm.mmproj-f16.gguf b/Qwen3-VL-8B-Thinking-norm.mmproj-f16.gguf new file mode 100644 index 0000000..ee81e13 --- /dev/null +++ b/Qwen3-VL-8B-Thinking-norm.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cf3c64c7d90e5fc5348b39ef7eaf1af8e5dac1a409fe1a0950472e6e2c9e3f8 +size 1159030336 diff --git a/README.md b/README.md new file mode 100644 index 0000000..968748c --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: fremko/Qwen3-VL-8B-Thinking-norm +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- vision +- qwen3-vl +- distillation +--- +## About + + + + + + + + + +static quants of https://huggingface.co/fremko/Qwen3-VL-8B-Thinking-norm + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VL-8B-Thinking-norm-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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-norm-GGUF/resolve/main/Qwen3-VL-8B-Thinking-norm.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-norm-GGUF/resolve/main/Qwen3-VL-8B-Thinking-norm.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-norm-GGUF/resolve/main/Qwen3-VL-8B-Thinking-norm.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-norm-GGUF/resolve/main/Qwen3-VL-8B-Thinking-norm.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-norm-GGUF/resolve/main/Qwen3-VL-8B-Thinking-norm.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-norm-GGUF/resolve/main/Qwen3-VL-8B-Thinking-norm.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-norm-GGUF/resolve/main/Qwen3-VL-8B-Thinking-norm.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-norm-GGUF/resolve/main/Qwen3-VL-8B-Thinking-norm.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-norm-GGUF/resolve/main/Qwen3-VL-8B-Thinking-norm.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-norm-GGUF/resolve/main/Qwen3-VL-8B-Thinking-norm.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-norm-GGUF/resolve/main/Qwen3-VL-8B-Thinking-norm.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-norm-GGUF/resolve/main/Qwen3-VL-8B-Thinking-norm.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-norm-GGUF/resolve/main/Qwen3-VL-8B-Thinking-norm.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Thinking-norm-GGUF/resolve/main/Qwen3-VL-8B-Thinking-norm.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. + +