commit c7ac67dac7755db198e5c61604794be9cbc2b2ff Author: ModelHub XC Date: Sun Jul 19 16:36:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-VL-3B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..71227e5 --- /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 +Qwen2.5-VL-3B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct.mmproj-fp16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-VL-3B-Instruct.IQ4_XS.gguf b/Qwen2.5-VL-3B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..2a43079 --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9702effd97ad5407cbc5f6c5f34bf79b9024bae60107665eeb353cd8cecc1f2b +size 1753185088 diff --git a/Qwen2.5-VL-3B-Instruct.Q2_K.gguf b/Qwen2.5-VL-3B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..69c1cb5 --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbf2431a4e50fe92583812855002c12e45da69543a39900aba64544edc1dcedf +size 1274755904 diff --git a/Qwen2.5-VL-3B-Instruct.Q3_K_L.gguf b/Qwen2.5-VL-3B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..536c2ff --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:557d68e674b3a78864fa3d24be823b092b80b965bc446039b791165bfe60c0dd +size 1707391808 diff --git a/Qwen2.5-VL-3B-Instruct.Q3_K_M.gguf b/Qwen2.5-VL-3B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..f111dee --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b4a6bca2cb738975edc9bf98ec54f7cb382e1aae31a22d953554466ed64eb7a +size 1590475584 diff --git a/Qwen2.5-VL-3B-Instruct.Q3_K_S.gguf b/Qwen2.5-VL-3B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..bb2181d --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:912dcb5e2a801c1c176610139f0026b932bc0e193fa9c9dabef4a7254c0343c2 +size 1454357312 diff --git a/Qwen2.5-VL-3B-Instruct.Q4_K_M.gguf b/Qwen2.5-VL-3B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..e166691 --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eadaae199d4d4720bd6e4b205cf13a46f5d8b86e6740af98950b21aa19dcfceb +size 1929902912 diff --git a/Qwen2.5-VL-3B-Instruct.Q4_K_S.gguf b/Qwen2.5-VL-3B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..dd299fc --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:891dd4d3a30c7cdac0eddb4defec0f0ae469135ff409d53c2d9b9244a073daa4 +size 1834384192 diff --git a/Qwen2.5-VL-3B-Instruct.Q5_K_M.gguf b/Qwen2.5-VL-3B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..2eff8b1 --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63e6fdbec1efdf7abb9e47f617cb237e20849ea81ee362609b2c3801b79b9aa4 +size 2224814912 diff --git a/Qwen2.5-VL-3B-Instruct.Q5_K_S.gguf b/Qwen2.5-VL-3B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..d35b7d6 --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c1e6cd1dd10d0ab3dd5d0dc553167be3286777f39bfee43f1b4f313142e345d +size 2169666368 diff --git a/Qwen2.5-VL-3B-Instruct.Q6_K.gguf b/Qwen2.5-VL-3B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..ba74f07 --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:519f20aa6a83274c31d1a9a4e27998e9b0177eb1f041c3ce2127f5c198686d65 +size 2538158912 diff --git a/Qwen2.5-VL-3B-Instruct.Q8_0.gguf b/Qwen2.5-VL-3B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..00d1c2f --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:830610d5942bd2bfae64ff77bd70b1f39cfd9b098f0603fd7098f311a251dcae +size 3285476160 diff --git a/Qwen2.5-VL-3B-Instruct.f16.gguf b/Qwen2.5-VL-3B-Instruct.f16.gguf new file mode 100644 index 0000000..0b78aeb --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e1a86552132c518eb6dd60819f45286ab131bd5a37817a60d19a7ff7b6124b5 +size 6178317120 diff --git a/Qwen2.5-VL-3B-Instruct.mmproj-fp16.gguf b/Qwen2.5-VL-3B-Instruct.mmproj-fp16.gguf new file mode 100644 index 0000000..66991eb --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct.mmproj-fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:747ca564db62e0903006a6d9bd31a0d55f85ed6afd919c7b0e55496983705e75 +size 1338428544 diff --git a/README.md b/README.md new file mode 100644 index 0000000..26dca4e --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Qwen/Qwen2.5-VL-3B-Instruct +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-VL-3B-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-VL-3B-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/Qwen2.5-VL-3B-Instruct-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct.mmproj-fp16.gguf) | mmproj-fp16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct.f16.gguf) | f16 | 6.3 | 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. + +