commit 8cbd2ea5950a8b177670b2ffe1100709efbd80d4 Author: ModelHub XC Date: Tue Oct 13 23:08:22 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-VL-4B-V1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ffa3e01 --- /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-V1.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-V1.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-V1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-V1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-V1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-V1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-V1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-V1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-V1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-V1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-V1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-V1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-V1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-V1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VL-4B-V1.IQ4_XS.gguf b/Qwen3-VL-4B-V1.IQ4_XS.gguf new file mode 100644 index 0000000..659d918 --- /dev/null +++ b/Qwen3-VL-4B-V1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50f9b53ef58f4428cf160a9b78c28f1c317d3229ed404cc23de90e1316913448 +size 2286318048 diff --git a/Qwen3-VL-4B-V1.Q2_K.gguf b/Qwen3-VL-4B-V1.Q2_K.gguf new file mode 100644 index 0000000..ae639f7 --- /dev/null +++ b/Qwen3-VL-4B-V1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e601a07b10fbdea7ba23afedf0f17ffb2469873fab3223a705fda8de304ebbb +size 1669501408 diff --git a/Qwen3-VL-4B-V1.Q3_K_L.gguf b/Qwen3-VL-4B-V1.Q3_K_L.gguf new file mode 100644 index 0000000..f4c4298 --- /dev/null +++ b/Qwen3-VL-4B-V1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0f92668304c22326449ee58a5a758d104fe99f0cf191818acc81a12f19d710d +size 2239787488 diff --git a/Qwen3-VL-4B-V1.Q3_K_M.gguf b/Qwen3-VL-4B-V1.Q3_K_M.gguf new file mode 100644 index 0000000..ac8e1c2 --- /dev/null +++ b/Qwen3-VL-4B-V1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a36ca1b307707ef601464dbfa0a8d32acabfc9fee506184e0737398321419e1d +size 2075619808 diff --git a/Qwen3-VL-4B-V1.Q3_K_S.gguf b/Qwen3-VL-4B-V1.Q3_K_S.gguf new file mode 100644 index 0000000..7f57974 --- /dev/null +++ b/Qwen3-VL-4B-V1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:180acc6213c6936e203838c7873cc54be4961dee645cf61f5c6606364a93d10b +size 1886999008 diff --git a/Qwen3-VL-4B-V1.Q4_K_M.gguf b/Qwen3-VL-4B-V1.Q4_K_M.gguf new file mode 100644 index 0000000..c8c7139 --- /dev/null +++ b/Qwen3-VL-4B-V1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c24469fe20181b724d8276f316efe762eaa95691fe7d069a50de2471e1cf455 +size 2497282528 diff --git a/Qwen3-VL-4B-V1.Q4_K_S.gguf b/Qwen3-VL-4B-V1.Q4_K_S.gguf new file mode 100644 index 0000000..31f6db5 --- /dev/null +++ b/Qwen3-VL-4B-V1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28a60d1eb589217a6165a7b30921e990e90b3c9d8372606fcb4007d29bb3611c +size 2383311328 diff --git a/Qwen3-VL-4B-V1.Q5_K_M.gguf b/Qwen3-VL-4B-V1.Q5_K_M.gguf new file mode 100644 index 0000000..9cdb9e2 --- /dev/null +++ b/Qwen3-VL-4B-V1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bb2552c64143554924d8cd65fccdf1b9440878b77eec549b872f1b7e7a34eee +size 2889515488 diff --git a/Qwen3-VL-4B-V1.Q5_K_S.gguf b/Qwen3-VL-4B-V1.Q5_K_S.gguf new file mode 100644 index 0000000..a64d982 --- /dev/null +++ b/Qwen3-VL-4B-V1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b046da97567cc9fa856daf7c3a19e10e4441683d7347ea5f4a5aeb5261f93f7 +size 2823713248 diff --git a/Qwen3-VL-4B-V1.Q6_K.gguf b/Qwen3-VL-4B-V1.Q6_K.gguf new file mode 100644 index 0000000..1ba622d --- /dev/null +++ b/Qwen3-VL-4B-V1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d777fde9a32cb17253987187b6d7cffcc14ca55846f799ba5777825b4d5dcc5b +size 3306263008 diff --git a/Qwen3-VL-4B-V1.Q8_0.gguf b/Qwen3-VL-4B-V1.Q8_0.gguf new file mode 100644 index 0000000..a1bb3f0 --- /dev/null +++ b/Qwen3-VL-4B-V1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b46240ec5da345d84daf65a1a0614a1c29e152f5e1303e2d5cdb9afa4f50c366 +size 4280407008 diff --git a/Qwen3-VL-4B-V1.f16.gguf b/Qwen3-VL-4B-V1.f16.gguf new file mode 100644 index 0000000..d54075d --- /dev/null +++ b/Qwen3-VL-4B-V1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cf823bcad60a70fb68b3896d1d5f94ff534cf5ae88aba5313d12ca4fe198329 +size 8051287008 diff --git a/Qwen3-VL-4B-V1.mmproj-Q8_0.gguf b/Qwen3-VL-4B-V1.mmproj-Q8_0.gguf new file mode 100644 index 0000000..1ff320e --- /dev/null +++ b/Qwen3-VL-4B-V1.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70fdc401b16dfb350bd2d2f6b98268b5328cd8b63421c6b64b0c7c6532bec9eb +size 453974720 diff --git a/Qwen3-VL-4B-V1.mmproj-f16.gguf b/Qwen3-VL-4B-V1.mmproj-f16.gguf new file mode 100644 index 0000000..2887a8e --- /dev/null +++ b/Qwen3-VL-4B-V1.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3ba7f10d7dc1f6ea16dfee9133d58689cdb9f87fd6ca64894e1263e4b243f2a +size 836180672 diff --git a/README.md b/README.md new file mode 100644 index 0000000..877480e --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: Zaynoid/Qwen3-VL-4B-V1 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3_vl +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Zaynoid/Qwen3-VL-4B-V1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VL-4B-V1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-VL-4B-V1-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-V1-GGUF/resolve/main/Qwen3-VL-4B-V1.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.6 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-V1-GGUF/resolve/main/Qwen3-VL-4B-V1.mmproj-f16.gguf) | mmproj-f16 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-V1-GGUF/resolve/main/Qwen3-VL-4B-V1.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-V1-GGUF/resolve/main/Qwen3-VL-4B-V1.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-V1-GGUF/resolve/main/Qwen3-VL-4B-V1.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-V1-GGUF/resolve/main/Qwen3-VL-4B-V1.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-V1-GGUF/resolve/main/Qwen3-VL-4B-V1.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-V1-GGUF/resolve/main/Qwen3-VL-4B-V1.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-V1-GGUF/resolve/main/Qwen3-VL-4B-V1.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-V1-GGUF/resolve/main/Qwen3-VL-4B-V1.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-V1-GGUF/resolve/main/Qwen3-VL-4B-V1.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-V1-GGUF/resolve/main/Qwen3-VL-4B-V1.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-V1-GGUF/resolve/main/Qwen3-VL-4B-V1.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-V1-GGUF/resolve/main/Qwen3-VL-4B-V1.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. 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. + +