commit be5f836d1674a0ccb0fbf072d902362d8d9e3872 Author: ModelHub XC Date: Wed Jun 3 23:20:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LOCUS-Qwen3-VL-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0c5813e --- /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 +LOCUS-Qwen3-VL-4B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LOCUS-Qwen3-VL-4B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +LOCUS-Qwen3-VL-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LOCUS-Qwen3-VL-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LOCUS-Qwen3-VL-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LOCUS-Qwen3-VL-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LOCUS-Qwen3-VL-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LOCUS-Qwen3-VL-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LOCUS-Qwen3-VL-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LOCUS-Qwen3-VL-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LOCUS-Qwen3-VL-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LOCUS-Qwen3-VL-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LOCUS-Qwen3-VL-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LOCUS-Qwen3-VL-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LOCUS-Qwen3-VL-4B.IQ4_XS.gguf b/LOCUS-Qwen3-VL-4B.IQ4_XS.gguf new file mode 100644 index 0000000..21fed2a --- /dev/null +++ b/LOCUS-Qwen3-VL-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1651fe6b3d580880ff2d3f92efc8b2664a6b9ff1810ce7a0a74bd295588fafe9 +size 2492950432 diff --git a/LOCUS-Qwen3-VL-4B.Q2_K.gguf b/LOCUS-Qwen3-VL-4B.Q2_K.gguf new file mode 100644 index 0000000..945edd6 --- /dev/null +++ b/LOCUS-Qwen3-VL-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fac4b4c5d9db019af337cd63b38a21fb7442df436995efa5a4a97e666a8e1ef1 +size 1797127072 diff --git a/LOCUS-Qwen3-VL-4B.Q3_K_L.gguf b/LOCUS-Qwen3-VL-4B.Q3_K_L.gguf new file mode 100644 index 0000000..79a58b3 --- /dev/null +++ b/LOCUS-Qwen3-VL-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98834a5154ccba2b8dbec80870b4ca3d4f0536684981ae36fcebc609f9a6d6db +size 2406916512 diff --git a/LOCUS-Qwen3-VL-4B.Q3_K_M.gguf b/LOCUS-Qwen3-VL-4B.Q3_K_M.gguf new file mode 100644 index 0000000..9d8dcf2 --- /dev/null +++ b/LOCUS-Qwen3-VL-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a542d96d3ae3e6a048959f743bb34608ac5f5c9a7a04a95049034846f4ae421e +size 2242748832 diff --git a/LOCUS-Qwen3-VL-4B.Q3_K_S.gguf b/LOCUS-Qwen3-VL-4B.Q3_K_S.gguf new file mode 100644 index 0000000..3bde338 --- /dev/null +++ b/LOCUS-Qwen3-VL-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:864be6db67d86f33a6af76a900eabf6a98821977042b7053ad6df4b9ddfbd6de +size 2054128032 diff --git a/LOCUS-Qwen3-VL-4B.Q4_K_M.gguf b/LOCUS-Qwen3-VL-4B.Q4_K_M.gguf new file mode 100644 index 0000000..7d42c95 --- /dev/null +++ b/LOCUS-Qwen3-VL-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac0dbd22ce4a10183180c64e45cceeea6a5061085ebc08729f3f52235e631f01 +size 2716069792 diff --git a/LOCUS-Qwen3-VL-4B.Q4_K_S.gguf b/LOCUS-Qwen3-VL-4B.Q4_K_S.gguf new file mode 100644 index 0000000..62c1946 --- /dev/null +++ b/LOCUS-Qwen3-VL-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:893ff2b55da88e4f88d919c71e1a893c3f71a903f5f6cf63bf921cf78d130ce3 +size 2602098592 diff --git a/LOCUS-Qwen3-VL-4B.Q5_K_M.gguf b/LOCUS-Qwen3-VL-4B.Q5_K_M.gguf new file mode 100644 index 0000000..d7ac47a --- /dev/null +++ b/LOCUS-Qwen3-VL-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06c64705c28d67652853f764c10424fcdcf5752e947842fe63e5a425cb6ffac0 +size 3156922272 diff --git a/LOCUS-Qwen3-VL-4B.Q5_K_S.gguf b/LOCUS-Qwen3-VL-4B.Q5_K_S.gguf new file mode 100644 index 0000000..7977b09 --- /dev/null +++ b/LOCUS-Qwen3-VL-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:393ad7258c6b02f81b7d27a5df2fc2a07ce925615fa923b6565eeacb93970179 +size 3091120032 diff --git a/LOCUS-Qwen3-VL-4B.Q6_K.gguf b/LOCUS-Qwen3-VL-4B.Q6_K.gguf new file mode 100644 index 0000000..9afa123 --- /dev/null +++ b/LOCUS-Qwen3-VL-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb6175f7b12d7b08d9bb79763e7325197ef7d34f3d920d5fc0019063e00424ce +size 3625328032 diff --git a/LOCUS-Qwen3-VL-4B.Q8_0.gguf b/LOCUS-Qwen3-VL-4B.Q8_0.gguf new file mode 100644 index 0000000..e4d6f2c --- /dev/null +++ b/LOCUS-Qwen3-VL-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a301a45a7eeda7292ecd64a0132acd8cc8b5f777ffd146517c769b4a1f2eccf +size 4693672352 diff --git a/LOCUS-Qwen3-VL-4B.f16.gguf b/LOCUS-Qwen3-VL-4B.f16.gguf new file mode 100644 index 0000000..55bb1b9 --- /dev/null +++ b/LOCUS-Qwen3-VL-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a119728b921401adf2e29dd7581ad63291411b8ef9af3538a2e63073662bf24 +size 8829198752 diff --git a/LOCUS-Qwen3-VL-4B.mmproj-Q8_0.gguf b/LOCUS-Qwen3-VL-4B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..2a4a6dc --- /dev/null +++ b/LOCUS-Qwen3-VL-4B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:794760033e0e25437cfd95b0495e8bee8c7a46cea1dece9039c9b8f47d8d524e +size 453974176 diff --git a/LOCUS-Qwen3-VL-4B.mmproj-f16.gguf b/LOCUS-Qwen3-VL-4B.mmproj-f16.gguf new file mode 100644 index 0000000..5f5a93e --- /dev/null +++ b/LOCUS-Qwen3-VL-4B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35c9f9bc71f689a5705ebafbe6a458999a94fb22e25b95868cc8943dde27cc01 +size 836180128 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7824521 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: gulitaozhou/LOCUS-Qwen3-VL-4B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/gulitaozhou/LOCUS-Qwen3-VL-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LOCUS-Qwen3-VL-4B-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/LOCUS-Qwen3-VL-4B-GGUF/resolve/main/LOCUS-Qwen3-VL-4B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.6 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/LOCUS-Qwen3-VL-4B-GGUF/resolve/main/LOCUS-Qwen3-VL-4B.mmproj-f16.gguf) | mmproj-f16 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/LOCUS-Qwen3-VL-4B-GGUF/resolve/main/LOCUS-Qwen3-VL-4B.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/LOCUS-Qwen3-VL-4B-GGUF/resolve/main/LOCUS-Qwen3-VL-4B.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/LOCUS-Qwen3-VL-4B-GGUF/resolve/main/LOCUS-Qwen3-VL-4B.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LOCUS-Qwen3-VL-4B-GGUF/resolve/main/LOCUS-Qwen3-VL-4B.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/LOCUS-Qwen3-VL-4B-GGUF/resolve/main/LOCUS-Qwen3-VL-4B.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/LOCUS-Qwen3-VL-4B-GGUF/resolve/main/LOCUS-Qwen3-VL-4B.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LOCUS-Qwen3-VL-4B-GGUF/resolve/main/LOCUS-Qwen3-VL-4B.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LOCUS-Qwen3-VL-4B-GGUF/resolve/main/LOCUS-Qwen3-VL-4B.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/LOCUS-Qwen3-VL-4B-GGUF/resolve/main/LOCUS-Qwen3-VL-4B.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LOCUS-Qwen3-VL-4B-GGUF/resolve/main/LOCUS-Qwen3-VL-4B.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LOCUS-Qwen3-VL-4B-GGUF/resolve/main/LOCUS-Qwen3-VL-4B.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LOCUS-Qwen3-VL-4B-GGUF/resolve/main/LOCUS-Qwen3-VL-4B.f16.gguf) | f16 | 8.9 | 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. + +