commit 0fd2ee9b8fadc5b1a67f700b04134036bb20c911 Author: ModelHub XC Date: Thu Apr 16 14:52:04 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-VL-8B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e4d9287 --- /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-8B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VL-8B-Instruct.IQ4_XS.gguf b/Qwen3-VL-8B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..b0e00f7 --- /dev/null +++ b/Qwen3-VL-8B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4598f8446414ad0702480fdeb51c9d055171e2721d3b3b57245f46c992e605b6 +size 4593298048 diff --git a/Qwen3-VL-8B-Instruct.Q2_K.gguf b/Qwen3-VL-8B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..6bb8884 --- /dev/null +++ b/Qwen3-VL-8B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:814989d8813972faab06eda27e5fb9c2b65145dbde23b6da3dd5f12ebdf1f435 +size 3281734272 diff --git a/Qwen3-VL-8B-Instruct.Q3_K_L.gguf b/Qwen3-VL-8B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..6168672 --- /dev/null +++ b/Qwen3-VL-8B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a62d19b729e3f67073a8a715b53da021187092652bf4b00793ce6a439aeede30 +size 4431395456 diff --git a/Qwen3-VL-8B-Instruct.Q3_K_M.gguf b/Qwen3-VL-8B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..e4e5e93 --- /dev/null +++ b/Qwen3-VL-8B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99c2178fe3653abe789e74f23d66f41cb438428f85c778754d2e4edf2655880d +size 4124162688 diff --git a/Qwen3-VL-8B-Instruct.Q3_K_S.gguf b/Qwen3-VL-8B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..effb33d --- /dev/null +++ b/Qwen3-VL-8B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9661ceb5a384cb9c143d934ec9a075c5376c4112e67f90ce44605c872b548116 +size 3769612928 diff --git a/Qwen3-VL-8B-Instruct.Q4_K_M.gguf b/Qwen3-VL-8B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..f202d16 --- /dev/null +++ b/Qwen3-VL-8B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:659ea2c20fe881bba78e6c7a41dc206ab4de993b3df80f554c18b098b673792e +size 5027785344 diff --git a/Qwen3-VL-8B-Instruct.Q4_K_S.gguf b/Qwen3-VL-8B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..e2ebf88 --- /dev/null +++ b/Qwen3-VL-8B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c34ee94477227e62bed8f7e817304e4fee9158556b6e67ba54fdeb381e483cc +size 4802013824 diff --git a/Qwen3-VL-8B-Instruct.Q5_K_M.gguf b/Qwen3-VL-8B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..061865b --- /dev/null +++ b/Qwen3-VL-8B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0caa99de2c7db0b60dfa529017186fd200b83b31a8a921aa6a91bada13abe3f +size 5851114112 diff --git a/Qwen3-VL-8B-Instruct.Q5_K_S.gguf b/Qwen3-VL-8B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..348f798 --- /dev/null +++ b/Qwen3-VL-8B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21138badb2adbbd83263f40bd85e4ea1e882b26092a1436a729c2b005b53108b +size 5720763008 diff --git a/Qwen3-VL-8B-Instruct.Q6_K.gguf b/Qwen3-VL-8B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..99b93fc --- /dev/null +++ b/Qwen3-VL-8B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d363f13a2c751eb9f1cba3a1700f77e0e09560a211386f202e8f7d7dae0f08cc +size 6725900928 diff --git a/Qwen3-VL-8B-Instruct.Q8_0.gguf b/Qwen3-VL-8B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..b958204 --- /dev/null +++ b/Qwen3-VL-8B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2370e7ec38c2ff0ee8b5aefaccbb86018a7bf44381a4970a0039832a9016ca2d +size 8709520000 diff --git a/Qwen3-VL-8B-Instruct.f16.gguf b/Qwen3-VL-8B-Instruct.f16.gguf new file mode 100644 index 0000000..d6f28be --- /dev/null +++ b/Qwen3-VL-8B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:974fbb1092d378c2dafd7fc9e823a892f02b927b19e0d09544faf68f82bda0f9 +size 16388045440 diff --git a/Qwen3-VL-8B-Instruct.mmproj-Q8_0.gguf b/Qwen3-VL-8B-Instruct.mmproj-Q8_0.gguf new file mode 100644 index 0000000..88a2e80 --- /dev/null +++ b/Qwen3-VL-8B-Instruct.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e848608a42de7e514803662b922f3835ce4191cde2709af1a2882d682c67718 +size 752289824 diff --git a/Qwen3-VL-8B-Instruct.mmproj-f16.gguf b/Qwen3-VL-8B-Instruct.mmproj-f16.gguf new file mode 100644 index 0000000..bf4d8c1 --- /dev/null +++ b/Qwen3-VL-8B-Instruct.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c3872ce326ac133cf3c383c83e84c76f03bd5c35d1789a746fa7b4b13f69229 +size 1159029920 diff --git a/README.md b/README.md new file mode 100644 index 0000000..edaf13a --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: Qwen/Qwen3-VL-8B-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-8B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VL-8B-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-VL-8B-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-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct.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. + +