commit d5924c912d17f2252c1ce4d3d6ad865ab95d039b Author: ModelHub XC Date: Thu Jul 16 17:37:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2-VL-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2da748e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Qwen2-VL-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-7B.mmproj-fp16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2-VL-7B.IQ4_XS.gguf b/Qwen2-VL-7B.IQ4_XS.gguf new file mode 100644 index 0000000..c389053 --- /dev/null +++ b/Qwen2-VL-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44b1aec65c72a289aab8cf2062d009186c3e3728d3a2f5a9f7519b3d7112f120 +size 4250297376 diff --git a/Qwen2-VL-7B.Q2_K.gguf b/Qwen2-VL-7B.Q2_K.gguf new file mode 100644 index 0000000..74610af --- /dev/null +++ b/Qwen2-VL-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88c58d0a9fdb826dfc3c807e11b8b4ec3e02f9b1d795ac7cff10f01f7e368b1a +size 3015939104 diff --git a/Qwen2-VL-7B.Q3_K_L.gguf b/Qwen2-VL-7B.Q3_K_L.gguf new file mode 100644 index 0000000..f291639 --- /dev/null +++ b/Qwen2-VL-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:306332c4f019b06f810a99e427af804cfc394e80562d4e94c3616ea8dad8a16a +size 4088458272 diff --git a/Qwen2-VL-7B.Q3_K_M.gguf b/Qwen2-VL-7B.Q3_K_M.gguf new file mode 100644 index 0000000..d1c1f80 --- /dev/null +++ b/Qwen2-VL-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80da697974b9f85dc9898223f96088b51d77bcf18a2f0ff4d9e2e0828905cfde +size 3808390176 diff --git a/Qwen2-VL-7B.Q3_K_S.gguf b/Qwen2-VL-7B.Q3_K_S.gguf new file mode 100644 index 0000000..a8d14df --- /dev/null +++ b/Qwen2-VL-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eedc6d88333dcd77665bbb9e7fe9d95c1c17ee8ee596b7d75928b3883315405 +size 3492367392 diff --git a/Qwen2-VL-7B.Q4_K_M.gguf b/Qwen2-VL-7B.Q4_K_M.gguf new file mode 100644 index 0000000..ffd1529 --- /dev/null +++ b/Qwen2-VL-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:256627270a3f619cde5f302d20aa8a981e0be6d720f60a85dc09734e2ed0686e +size 4683072544 diff --git a/Qwen2-VL-7B.Q4_K_S.gguf b/Qwen2-VL-7B.Q4_K_S.gguf new file mode 100644 index 0000000..b05107f --- /dev/null +++ b/Qwen2-VL-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41defa650cd79a91dc918b2340df6b5f26668de062865456de5d035eb14d950c +size 4457767968 diff --git a/Qwen2-VL-7B.Q5_K_M.gguf b/Qwen2-VL-7B.Q5_K_M.gguf new file mode 100644 index 0000000..3336529 --- /dev/null +++ b/Qwen2-VL-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cffcaca95c64ddc641998125fa54bdd9b343d013491746977608b09342ebe9d +size 5444830240 diff --git a/Qwen2-VL-7B.Q5_K_S.gguf b/Qwen2-VL-7B.Q5_K_S.gguf new file mode 100644 index 0000000..1f32e48 --- /dev/null +++ b/Qwen2-VL-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e520c8ba93655b757dc227e4bd837d5196333fb4651b165802c7049fe0fe8d6 +size 5315175456 diff --git a/Qwen2-VL-7B.Q6_K.gguf b/Qwen2-VL-7B.Q6_K.gguf new file mode 100644 index 0000000..7fe1043 --- /dev/null +++ b/Qwen2-VL-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a3dd2da7a1fca11b999502baa881b3f4f879e3047dfd6144ea6eed5bb8b8db2 +size 6254197792 diff --git a/Qwen2-VL-7B.Q8_0.gguf b/Qwen2-VL-7B.Q8_0.gguf new file mode 100644 index 0000000..a30ccdc --- /dev/null +++ b/Qwen2-VL-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ded4ee68d8a396e5e3a2b1c1e1f3fe62559ef69ed42c2ae53d4e35b7f628f63e +size 8098524192 diff --git a/Qwen2-VL-7B.f16.gguf b/Qwen2-VL-7B.f16.gguf new file mode 100644 index 0000000..13c86cd --- /dev/null +++ b/Qwen2-VL-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fb525803b9f95bfb3c9ac6975fe5540a648456a08ed3939da5179884d7b7f74 +size 15237852192 diff --git a/Qwen2-VL-7B.mmproj-fp16.gguf b/Qwen2-VL-7B.mmproj-fp16.gguf new file mode 100644 index 0000000..dfdfe72 --- /dev/null +++ b/Qwen2-VL-7B.mmproj-fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7838bec59860930af7f6a9889d3e31445003557140144380a1a5fa6a09110c3 +size 1352635904 diff --git a/README.md b/README.md new file mode 100644 index 0000000..75199f7 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Qwen/Qwen2-VL-7B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- multimodal +--- +## About + + + + + + +static quants of https://huggingface.co/Qwen/Qwen2-VL-7B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2-VL-7B-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/Qwen2-VL-7B-GGUF/resolve/main/Qwen2-VL-7B.mmproj-fp16.gguf) | mmproj-fp16 | 1.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-7B-GGUF/resolve/main/Qwen2-VL-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-7B-GGUF/resolve/main/Qwen2-VL-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-7B-GGUF/resolve/main/Qwen2-VL-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-7B-GGUF/resolve/main/Qwen2-VL-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-7B-GGUF/resolve/main/Qwen2-VL-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-7B-GGUF/resolve/main/Qwen2-VL-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-7B-GGUF/resolve/main/Qwen2-VL-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-7B-GGUF/resolve/main/Qwen2-VL-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-7B-GGUF/resolve/main/Qwen2-VL-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-7B-GGUF/resolve/main/Qwen2-VL-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-7B-GGUF/resolve/main/Qwen2-VL-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-7B-GGUF/resolve/main/Qwen2-VL-7B.f16.gguf) | f16 | 15.3 | 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. + +