commit c5ec3f302432b3a60d5f4fc25160a603e303ee7e Author: ModelHub XC Date: Wed Sep 2 21:36:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-VL-4B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0bd593e --- /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-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VL-4B-Instruct.IQ4_XS.gguf b/Qwen3-VL-4B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..4d8492f --- /dev/null +++ b/Qwen3-VL-4B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c419bfece5f41dd2c8d9cbefffc22cfd25c4130906c0b03f24204cc87e06dba8 +size 2286317664 diff --git a/Qwen3-VL-4B-Instruct.Q2_K.gguf b/Qwen3-VL-4B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..0761448 --- /dev/null +++ b/Qwen3-VL-4B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1417df898d126eede9e4f37152c405e0b00bf693844c60cfa49067ed8eb22f0b +size 1669501024 diff --git a/Qwen3-VL-4B-Instruct.Q3_K_L.gguf b/Qwen3-VL-4B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..1fb58de --- /dev/null +++ b/Qwen3-VL-4B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ede65b7f5791ea72fefcc6e4d6f98fe00824f916b420a93b12ece93604d4113 +size 2239787104 diff --git a/Qwen3-VL-4B-Instruct.Q3_K_M.gguf b/Qwen3-VL-4B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..93f9212 --- /dev/null +++ b/Qwen3-VL-4B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e7490f141def2bd63748ffb77ad12e8b6744c0f03796e268469c2aa3d9c5998 +size 2075619424 diff --git a/Qwen3-VL-4B-Instruct.Q3_K_S.gguf b/Qwen3-VL-4B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..31c97d4 --- /dev/null +++ b/Qwen3-VL-4B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fa5d1f0e73a8bee00f1e286c21f0c8d38ddad4d1488a2713e57151002445859 +size 1886998624 diff --git a/Qwen3-VL-4B-Instruct.Q4_K_M.gguf b/Qwen3-VL-4B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..cf17e6a --- /dev/null +++ b/Qwen3-VL-4B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f6cb2158d0cf9e31451c9bf58d2728a7553420368a150635995301939e1c7f0 +size 2497282144 diff --git a/Qwen3-VL-4B-Instruct.Q4_K_S.gguf b/Qwen3-VL-4B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..32be2f4 --- /dev/null +++ b/Qwen3-VL-4B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15e83425a6b375ae99cafc1643a6bfa3504380ae9ec80133e2a9227db8bff716 +size 2383310944 diff --git a/Qwen3-VL-4B-Instruct.Q5_K_M.gguf b/Qwen3-VL-4B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..4274014 --- /dev/null +++ b/Qwen3-VL-4B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a571c766fb681c2ff0a7603156e3e15f9bf6628822f178bf75c3461bcaf380a +size 2889515104 diff --git a/Qwen3-VL-4B-Instruct.Q5_K_S.gguf b/Qwen3-VL-4B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..3191bfd --- /dev/null +++ b/Qwen3-VL-4B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b31dbe140b3a68c1bf6defa84a4bb28356aad8b441b76fa839a53f0b6514aa6e +size 2823712864 diff --git a/Qwen3-VL-4B-Instruct.Q6_K.gguf b/Qwen3-VL-4B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..26cec2c --- /dev/null +++ b/Qwen3-VL-4B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c7242b5961bbb1d753486c2dd00c8e7d5a25fa6cebe3958ce84bc607bc4973a +size 3306262624 diff --git a/Qwen3-VL-4B-Instruct.Q8_0.gguf b/Qwen3-VL-4B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..8d3f006 --- /dev/null +++ b/Qwen3-VL-4B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4b185587694794aa9b4f754fae12d6c2f9544d8d729f846e7c5ac19d780e29e +size 4280406624 diff --git a/Qwen3-VL-4B-Instruct.f16.gguf b/Qwen3-VL-4B-Instruct.f16.gguf new file mode 100644 index 0000000..44bc22d --- /dev/null +++ b/Qwen3-VL-4B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3b129876bf51ba50b5df5b489646050ce7b8cb4f01f3b8caf049affe05a50c7 +size 8051286624 diff --git a/Qwen3-VL-4B-Instruct.mmproj-Q8_0.gguf b/Qwen3-VL-4B-Instruct.mmproj-Q8_0.gguf new file mode 100644 index 0000000..2eceecd --- /dev/null +++ b/Qwen3-VL-4B-Instruct.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8da3cc6ea23d60daa84802909a1102b9f5e9c875483d38c07f57723a4cbd5fe +size 453974304 diff --git a/Qwen3-VL-4B-Instruct.mmproj-f16.gguf b/Qwen3-VL-4B-Instruct.mmproj-f16.gguf new file mode 100644 index 0000000..6629a25 --- /dev/null +++ b/Qwen3-VL-4B-Instruct.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d5e698305f6e092c682d3e8e8deb1db88915e69a7dd66c0279e7ce810bfee48 +size 836180256 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6a59a51 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: Qwen/Qwen3-VL-4B-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VL-4B-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-VL-4B-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-Instruct-GGUF/resolve/main/Qwen3-VL-4B-Instruct.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.6 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-GGUF/resolve/main/Qwen3-VL-4B-Instruct.mmproj-f16.gguf) | mmproj-f16 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-GGUF/resolve/main/Qwen3-VL-4B-Instruct.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-GGUF/resolve/main/Qwen3-VL-4B-Instruct.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-GGUF/resolve/main/Qwen3-VL-4B-Instruct.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-GGUF/resolve/main/Qwen3-VL-4B-Instruct.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-GGUF/resolve/main/Qwen3-VL-4B-Instruct.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-GGUF/resolve/main/Qwen3-VL-4B-Instruct.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-GGUF/resolve/main/Qwen3-VL-4B-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-GGUF/resolve/main/Qwen3-VL-4B-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-GGUF/resolve/main/Qwen3-VL-4B-Instruct.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-GGUF/resolve/main/Qwen3-VL-4B-Instruct.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-GGUF/resolve/main/Qwen3-VL-4B-Instruct.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-GGUF/resolve/main/Qwen3-VL-4B-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. + +