commit 04ab7f403fdbdbe1034073cfd7a277db6a182daa Author: ModelHub XC Date: Fri Jul 17 07:07:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-VL-4B-YOYO-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..567358c --- /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-4B-YOYO-Instruct.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-YOYO-Instruct.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-YOYO-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-YOYO-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-YOYO-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-YOYO-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-YOYO-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-YOYO-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-YOYO-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-YOYO-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-YOYO-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-YOYO-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-YOYO-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-YOYO-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VL-4B-YOYO-Instruct.IQ4_XS.gguf b/Qwen3-VL-4B-YOYO-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..3e49ac2 --- /dev/null +++ b/Qwen3-VL-4B-YOYO-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c20d9e7adfd63a27b15a8fcb9dc973ebe326a807fd61f97c0b5011db7c0e5953 +size 2286318400 diff --git a/Qwen3-VL-4B-YOYO-Instruct.Q2_K.gguf b/Qwen3-VL-4B-YOYO-Instruct.Q2_K.gguf new file mode 100644 index 0000000..60d74a1 --- /dev/null +++ b/Qwen3-VL-4B-YOYO-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c9e0364cade87a9d7fc5b828bc4658ccc2d5fd4c279ef133f796ce89874b973 +size 1669501760 diff --git a/Qwen3-VL-4B-YOYO-Instruct.Q3_K_L.gguf b/Qwen3-VL-4B-YOYO-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..c478bcf --- /dev/null +++ b/Qwen3-VL-4B-YOYO-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:063e17ceba1567094817fdea82d07a02ccfb9a7ffeab17882d634cc07006fd38 +size 2239787840 diff --git a/Qwen3-VL-4B-YOYO-Instruct.Q3_K_M.gguf b/Qwen3-VL-4B-YOYO-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..0acc102 --- /dev/null +++ b/Qwen3-VL-4B-YOYO-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:687c1fc823cdc61f6bd4ea10550d2a9003c9c92bfeae2ce8de8c18530a2edd77 +size 2075620160 diff --git a/Qwen3-VL-4B-YOYO-Instruct.Q3_K_S.gguf b/Qwen3-VL-4B-YOYO-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..d010370 --- /dev/null +++ b/Qwen3-VL-4B-YOYO-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b2a4656a6059781866c769dca24b84c315a6a3ea7f5382b3c1ba468c0fa4843 +size 1886999360 diff --git a/Qwen3-VL-4B-YOYO-Instruct.Q4_K_M.gguf b/Qwen3-VL-4B-YOYO-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..417c2e1 --- /dev/null +++ b/Qwen3-VL-4B-YOYO-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9869a164056afc03bb78c71ac432907dab35c73d241b4e72937bbad8db175f68 +size 2497282880 diff --git a/Qwen3-VL-4B-YOYO-Instruct.Q4_K_S.gguf b/Qwen3-VL-4B-YOYO-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..7d2938c --- /dev/null +++ b/Qwen3-VL-4B-YOYO-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11130ce96a11c618583a7260c7a8c1676770f10027f4aabdf8f35e4b0b7097c7 +size 2383311680 diff --git a/Qwen3-VL-4B-YOYO-Instruct.Q5_K_M.gguf b/Qwen3-VL-4B-YOYO-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..b3b6d2a --- /dev/null +++ b/Qwen3-VL-4B-YOYO-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7ceb733775af350653f091bdd488b630cb110ed30c89b4cf4ac55b5434a4df5 +size 2889515840 diff --git a/Qwen3-VL-4B-YOYO-Instruct.Q5_K_S.gguf b/Qwen3-VL-4B-YOYO-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..183d9c4 --- /dev/null +++ b/Qwen3-VL-4B-YOYO-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d38d3a599e6cee7d3263adb8ee21d5957d00dca8e3235ab34f716e0733b3a51 +size 2823713600 diff --git a/Qwen3-VL-4B-YOYO-Instruct.Q6_K.gguf b/Qwen3-VL-4B-YOYO-Instruct.Q6_K.gguf new file mode 100644 index 0000000..b67ef50 --- /dev/null +++ b/Qwen3-VL-4B-YOYO-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f9b725f0b3d4b4f637c506a661dd71333fe58cd5e928f014ca27b987c1a3027 +size 3306263360 diff --git a/Qwen3-VL-4B-YOYO-Instruct.Q8_0.gguf b/Qwen3-VL-4B-YOYO-Instruct.Q8_0.gguf new file mode 100644 index 0000000..e14508d --- /dev/null +++ b/Qwen3-VL-4B-YOYO-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e335f8b153be393fd26277e4f15ee41d7950794fad026268b3d05e053c367c69 +size 4280407360 diff --git a/Qwen3-VL-4B-YOYO-Instruct.f16.gguf b/Qwen3-VL-4B-YOYO-Instruct.f16.gguf new file mode 100644 index 0000000..b8be964 --- /dev/null +++ b/Qwen3-VL-4B-YOYO-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c63a118261e31a1fdfd2af0072ffe416a7fcda2b561b2ba1c20edb755d141d39 +size 8051287360 diff --git a/Qwen3-VL-4B-YOYO-Instruct.mmproj-Q8_0.gguf b/Qwen3-VL-4B-YOYO-Instruct.mmproj-Q8_0.gguf new file mode 100644 index 0000000..389222a --- /dev/null +++ b/Qwen3-VL-4B-YOYO-Instruct.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:744dcf707087fc42ce15aad8ce6d7109763613042d0801985632a3b8490a94f3 +size 453975008 diff --git a/Qwen3-VL-4B-YOYO-Instruct.mmproj-f16.gguf b/Qwen3-VL-4B-YOYO-Instruct.mmproj-f16.gguf new file mode 100644 index 0000000..4159c44 --- /dev/null +++ b/Qwen3-VL-4B-YOYO-Instruct.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e04d6a71302f48ebc1723c1d0a6556b93fc5639bf7fb11197af2e2d0d2a6cce5 +size 836180960 diff --git a/README.md b/README.md new file mode 100644 index 0000000..aa1589b --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: YOYO-AI/Qwen3-VL-4B-YOYO-Instruct +language: +- en +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +--- +## About + + + + + + + + + +static quants of https://huggingface.co/YOYO-AI/Qwen3-VL-4B-YOYO-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VL-4B-YOYO-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-VL-4B-YOYO-Instruct-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-4B-YOYO-Instruct-GGUF/resolve/main/Qwen3-VL-4B-YOYO-Instruct.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.6 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-YOYO-Instruct-GGUF/resolve/main/Qwen3-VL-4B-YOYO-Instruct.mmproj-f16.gguf) | mmproj-f16 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-YOYO-Instruct-GGUF/resolve/main/Qwen3-VL-4B-YOYO-Instruct.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-YOYO-Instruct-GGUF/resolve/main/Qwen3-VL-4B-YOYO-Instruct.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-YOYO-Instruct-GGUF/resolve/main/Qwen3-VL-4B-YOYO-Instruct.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-YOYO-Instruct-GGUF/resolve/main/Qwen3-VL-4B-YOYO-Instruct.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-YOYO-Instruct-GGUF/resolve/main/Qwen3-VL-4B-YOYO-Instruct.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-YOYO-Instruct-GGUF/resolve/main/Qwen3-VL-4B-YOYO-Instruct.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-YOYO-Instruct-GGUF/resolve/main/Qwen3-VL-4B-YOYO-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-YOYO-Instruct-GGUF/resolve/main/Qwen3-VL-4B-YOYO-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-YOYO-Instruct-GGUF/resolve/main/Qwen3-VL-4B-YOYO-Instruct.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-YOYO-Instruct-GGUF/resolve/main/Qwen3-VL-4B-YOYO-Instruct.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-YOYO-Instruct-GGUF/resolve/main/Qwen3-VL-4B-YOYO-Instruct.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-YOYO-Instruct-GGUF/resolve/main/Qwen3-VL-4B-YOYO-Instruct.f16.gguf) | f16 | 8.2 | 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. + +