commit 1920c316e042d1fe8bdd2cbc0fb6e454966d6337 Author: ModelHub XC Date: Fri Oct 30 17:30:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-VL-8B-AutoSafe-120-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a3d9fb8 --- /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-AutoSafe-120.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-AutoSafe-120.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-AutoSafe-120.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-AutoSafe-120.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-AutoSafe-120.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-AutoSafe-120.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-AutoSafe-120.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-AutoSafe-120.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-AutoSafe-120.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-AutoSafe-120.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-AutoSafe-120.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-AutoSafe-120.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-AutoSafe-120.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VL-8B-AutoSafe-120.IQ4_XS.gguf b/Qwen3-VL-8B-AutoSafe-120.IQ4_XS.gguf new file mode 100644 index 0000000..182bb08 --- /dev/null +++ b/Qwen3-VL-8B-AutoSafe-120.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90036e378ed42dac8781ffe7d3a489680fd8fa976fb8ef0fd70435b248b54092 +size 4593297920 diff --git a/Qwen3-VL-8B-AutoSafe-120.Q2_K.gguf b/Qwen3-VL-8B-AutoSafe-120.Q2_K.gguf new file mode 100644 index 0000000..6d578f0 --- /dev/null +++ b/Qwen3-VL-8B-AutoSafe-120.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa9ee5a857a4f42b652b237ad1219da23b20fb6552a988a745a08956df34f2d1 +size 3281734144 diff --git a/Qwen3-VL-8B-AutoSafe-120.Q3_K_L.gguf b/Qwen3-VL-8B-AutoSafe-120.Q3_K_L.gguf new file mode 100644 index 0000000..0a5fb88 --- /dev/null +++ b/Qwen3-VL-8B-AutoSafe-120.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4639b368471d50238f46d2032b4f8b8a6d962c2891ab8e09885eb597144dfeaf +size 4431395328 diff --git a/Qwen3-VL-8B-AutoSafe-120.Q3_K_M.gguf b/Qwen3-VL-8B-AutoSafe-120.Q3_K_M.gguf new file mode 100644 index 0000000..68d8b76 --- /dev/null +++ b/Qwen3-VL-8B-AutoSafe-120.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d47ce720526dea7221b6e8530dea5a055eaea683d14537329848c9d2888c5e0d +size 4124162560 diff --git a/Qwen3-VL-8B-AutoSafe-120.Q3_K_S.gguf b/Qwen3-VL-8B-AutoSafe-120.Q3_K_S.gguf new file mode 100644 index 0000000..0106f6e --- /dev/null +++ b/Qwen3-VL-8B-AutoSafe-120.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e05522642964283dcb14cadea048ad846206a6815682be22a6091684e19a894 +size 3769612800 diff --git a/Qwen3-VL-8B-AutoSafe-120.Q4_K_M.gguf b/Qwen3-VL-8B-AutoSafe-120.Q4_K_M.gguf new file mode 100644 index 0000000..8a218c0 --- /dev/null +++ b/Qwen3-VL-8B-AutoSafe-120.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39b3f9c40a7c59db5953f4c63d546d084ea36a5b4ab91dbb85e7a7749bee063d +size 5027785216 diff --git a/Qwen3-VL-8B-AutoSafe-120.Q4_K_S.gguf b/Qwen3-VL-8B-AutoSafe-120.Q4_K_S.gguf new file mode 100644 index 0000000..4fa7a2c --- /dev/null +++ b/Qwen3-VL-8B-AutoSafe-120.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e5519070986d514e2ee954f684ef78fb22a82e28ef56024ae08ba0959039f7e +size 4802013696 diff --git a/Qwen3-VL-8B-AutoSafe-120.Q5_K_M.gguf b/Qwen3-VL-8B-AutoSafe-120.Q5_K_M.gguf new file mode 100644 index 0000000..427a850 --- /dev/null +++ b/Qwen3-VL-8B-AutoSafe-120.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6da6533700c6eb3d8e67a19ebff36ac18afe075ad2c29036c1449cc6a04c1769 +size 5851113984 diff --git a/Qwen3-VL-8B-AutoSafe-120.Q5_K_S.gguf b/Qwen3-VL-8B-AutoSafe-120.Q5_K_S.gguf new file mode 100644 index 0000000..ab4f9bf --- /dev/null +++ b/Qwen3-VL-8B-AutoSafe-120.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:befdc78097eb6417dc93f04e778ba2b48ecadb8ca56a5ac44e927f6391a93917 +size 5720762880 diff --git a/Qwen3-VL-8B-AutoSafe-120.Q6_K.gguf b/Qwen3-VL-8B-AutoSafe-120.Q6_K.gguf new file mode 100644 index 0000000..9b511e5 --- /dev/null +++ b/Qwen3-VL-8B-AutoSafe-120.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beb4e43739718272408edcf3a3a88fd9f305f966d7dd0e95951c6ad4e7524673 +size 6725900800 diff --git a/Qwen3-VL-8B-AutoSafe-120.Q8_0.gguf b/Qwen3-VL-8B-AutoSafe-120.Q8_0.gguf new file mode 100644 index 0000000..3bf5418 --- /dev/null +++ b/Qwen3-VL-8B-AutoSafe-120.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01896c304925b19a875654ab4654876e4cb63a1358b33d0041763a6b1ed5eeac +size 8709519872 diff --git a/Qwen3-VL-8B-AutoSafe-120.f16.gguf b/Qwen3-VL-8B-AutoSafe-120.f16.gguf new file mode 100644 index 0000000..63966e9 --- /dev/null +++ b/Qwen3-VL-8B-AutoSafe-120.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81331c0ce5d7fb32b92f534257f73de9f1a35ac6f5a5679127a7cb2ce606b17c +size 16388045312 diff --git a/Qwen3-VL-8B-AutoSafe-120.mmproj-Q8_0.gguf b/Qwen3-VL-8B-AutoSafe-120.mmproj-Q8_0.gguf new file mode 100644 index 0000000..d37b1bd --- /dev/null +++ b/Qwen3-VL-8B-AutoSafe-120.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31a06292fe86db4dc7c95cbcfea5d1d54d4bfedec0eb71639630bb23614a4eac +size 752289760 diff --git a/Qwen3-VL-8B-AutoSafe-120.mmproj-f16.gguf b/Qwen3-VL-8B-AutoSafe-120.mmproj-f16.gguf new file mode 100644 index 0000000..1bcd703 --- /dev/null +++ b/Qwen3-VL-8B-AutoSafe-120.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6813c33ffb51534f8c8eaa7075fb07e6312f1ab96e273dd581345143b19a8979 +size 1159029856 diff --git a/README.md b/README.md new file mode 100644 index 0000000..23d3c3c --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: XuankunRong/Qwen3-VL-8B-AutoSafe-120 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/XuankunRong/Qwen3-VL-8B-AutoSafe-120 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VL-8B-AutoSafe-120-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-AutoSafe-120-GGUF/resolve/main/Qwen3-VL-8B-AutoSafe-120.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-AutoSafe-120-GGUF/resolve/main/Qwen3-VL-8B-AutoSafe-120.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-AutoSafe-120-GGUF/resolve/main/Qwen3-VL-8B-AutoSafe-120.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-AutoSafe-120-GGUF/resolve/main/Qwen3-VL-8B-AutoSafe-120.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-AutoSafe-120-GGUF/resolve/main/Qwen3-VL-8B-AutoSafe-120.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-AutoSafe-120-GGUF/resolve/main/Qwen3-VL-8B-AutoSafe-120.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-AutoSafe-120-GGUF/resolve/main/Qwen3-VL-8B-AutoSafe-120.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-AutoSafe-120-GGUF/resolve/main/Qwen3-VL-8B-AutoSafe-120.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-AutoSafe-120-GGUF/resolve/main/Qwen3-VL-8B-AutoSafe-120.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-AutoSafe-120-GGUF/resolve/main/Qwen3-VL-8B-AutoSafe-120.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-AutoSafe-120-GGUF/resolve/main/Qwen3-VL-8B-AutoSafe-120.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-AutoSafe-120-GGUF/resolve/main/Qwen3-VL-8B-AutoSafe-120.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-AutoSafe-120-GGUF/resolve/main/Qwen3-VL-8B-AutoSafe-120.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-AutoSafe-120-GGUF/resolve/main/Qwen3-VL-8B-AutoSafe-120.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. Additional thanks to [@nicoboss](https://huggingface.co/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. + +