From 24a3ae814c63bacb5f03312c6360ebd17c1191d8 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 6 Sep 2026 22:04:16 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/Qwen2.5-VL-3B-DocIndo-GGUF Source: Original Platform --- .gitattributes | 47 +++++++++++++++++++++ Qwen2.5-VL-3B-DocIndo.IQ4_XS.gguf | 3 ++ Qwen2.5-VL-3B-DocIndo.Q2_K.gguf | 3 ++ Qwen2.5-VL-3B-DocIndo.Q3_K_L.gguf | 3 ++ Qwen2.5-VL-3B-DocIndo.Q3_K_M.gguf | 3 ++ Qwen2.5-VL-3B-DocIndo.Q3_K_S.gguf | 3 ++ Qwen2.5-VL-3B-DocIndo.Q4_K_M.gguf | 3 ++ Qwen2.5-VL-3B-DocIndo.Q4_K_S.gguf | 3 ++ Qwen2.5-VL-3B-DocIndo.Q5_K_M.gguf | 3 ++ Qwen2.5-VL-3B-DocIndo.Q5_K_S.gguf | 3 ++ Qwen2.5-VL-3B-DocIndo.Q6_K.gguf | 3 ++ Qwen2.5-VL-3B-DocIndo.Q8_0.gguf | 3 ++ Qwen2.5-VL-3B-DocIndo.f16.gguf | 3 ++ README.md | 69 +++++++++++++++++++++++++++++++ 14 files changed, 152 insertions(+) create mode 100644 .gitattributes create mode 100644 Qwen2.5-VL-3B-DocIndo.IQ4_XS.gguf create mode 100644 Qwen2.5-VL-3B-DocIndo.Q2_K.gguf create mode 100644 Qwen2.5-VL-3B-DocIndo.Q3_K_L.gguf create mode 100644 Qwen2.5-VL-3B-DocIndo.Q3_K_M.gguf create mode 100644 Qwen2.5-VL-3B-DocIndo.Q3_K_S.gguf create mode 100644 Qwen2.5-VL-3B-DocIndo.Q4_K_M.gguf create mode 100644 Qwen2.5-VL-3B-DocIndo.Q4_K_S.gguf create mode 100644 Qwen2.5-VL-3B-DocIndo.Q5_K_M.gguf create mode 100644 Qwen2.5-VL-3B-DocIndo.Q5_K_S.gguf create mode 100644 Qwen2.5-VL-3B-DocIndo.Q6_K.gguf create mode 100644 Qwen2.5-VL-3B-DocIndo.Q8_0.gguf create mode 100644 Qwen2.5-VL-3B-DocIndo.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..271415b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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-DocIndo.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-DocIndo.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-DocIndo.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-DocIndo.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-DocIndo.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-DocIndo.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-DocIndo.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-DocIndo.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-DocIndo.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-DocIndo.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-DocIndo.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-DocIndo.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-VL-3B-DocIndo.IQ4_XS.gguf b/Qwen2.5-VL-3B-DocIndo.IQ4_XS.gguf new file mode 100644 index 0000000..5f46715 --- /dev/null +++ b/Qwen2.5-VL-3B-DocIndo.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64f5571785669ebe6c6cceb30289c0702b593529d0aa0f6418dd7c0096365baa +size 1753185152 diff --git a/Qwen2.5-VL-3B-DocIndo.Q2_K.gguf b/Qwen2.5-VL-3B-DocIndo.Q2_K.gguf new file mode 100644 index 0000000..acf5ee3 --- /dev/null +++ b/Qwen2.5-VL-3B-DocIndo.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ef29898edec32a1221159bcbd91468948200175ad897e6939ab1aa4dfd395b2 +size 1274755968 diff --git a/Qwen2.5-VL-3B-DocIndo.Q3_K_L.gguf b/Qwen2.5-VL-3B-DocIndo.Q3_K_L.gguf new file mode 100644 index 0000000..4085ee1 --- /dev/null +++ b/Qwen2.5-VL-3B-DocIndo.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad6233fd2108416a27603556d9133b71d2b6eda1ca9b1ed4328d3545b2d5c5ba +size 1707391872 diff --git a/Qwen2.5-VL-3B-DocIndo.Q3_K_M.gguf b/Qwen2.5-VL-3B-DocIndo.Q3_K_M.gguf new file mode 100644 index 0000000..7e57741 --- /dev/null +++ b/Qwen2.5-VL-3B-DocIndo.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5a931d4969c6fb203a90a9966520a5a1547113bfc228ac9053b20ac510269dd +size 1590475648 diff --git a/Qwen2.5-VL-3B-DocIndo.Q3_K_S.gguf b/Qwen2.5-VL-3B-DocIndo.Q3_K_S.gguf new file mode 100644 index 0000000..ab165ba --- /dev/null +++ b/Qwen2.5-VL-3B-DocIndo.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aef8090c3d0ccc74a481fc9c8d4f3fb13f56bc55426ac84484e791b156f560d7 +size 1454357376 diff --git a/Qwen2.5-VL-3B-DocIndo.Q4_K_M.gguf b/Qwen2.5-VL-3B-DocIndo.Q4_K_M.gguf new file mode 100644 index 0000000..98934b4 --- /dev/null +++ b/Qwen2.5-VL-3B-DocIndo.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ef4211cf019cfda5a2ba13941c2f9294d614098975ff11c87a8ab45dcbb8dce +size 1929902976 diff --git a/Qwen2.5-VL-3B-DocIndo.Q4_K_S.gguf b/Qwen2.5-VL-3B-DocIndo.Q4_K_S.gguf new file mode 100644 index 0000000..8e7f946 --- /dev/null +++ b/Qwen2.5-VL-3B-DocIndo.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be1f339804c3f18d0e54a3f4180c7fa93fb3d9dd9b38c93a0a3ffd5d58385dd5 +size 1834384256 diff --git a/Qwen2.5-VL-3B-DocIndo.Q5_K_M.gguf b/Qwen2.5-VL-3B-DocIndo.Q5_K_M.gguf new file mode 100644 index 0000000..b2e3292 --- /dev/null +++ b/Qwen2.5-VL-3B-DocIndo.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d9c3bf57b3a593f405d879e065d44c2bd3ca6b82beb381fa1a85aaf182edcb6 +size 2224814976 diff --git a/Qwen2.5-VL-3B-DocIndo.Q5_K_S.gguf b/Qwen2.5-VL-3B-DocIndo.Q5_K_S.gguf new file mode 100644 index 0000000..6a16953 --- /dev/null +++ b/Qwen2.5-VL-3B-DocIndo.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d1982cbf079d8501bbebdce689b6c8ad59b32f0694dfeb81b70440f65b43bf5 +size 2169666432 diff --git a/Qwen2.5-VL-3B-DocIndo.Q6_K.gguf b/Qwen2.5-VL-3B-DocIndo.Q6_K.gguf new file mode 100644 index 0000000..543cf1d --- /dev/null +++ b/Qwen2.5-VL-3B-DocIndo.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2f283a79f7b0d12423db7c825cca33233310a9e99796b60abd5b8a410dfa675 +size 2538158976 diff --git a/Qwen2.5-VL-3B-DocIndo.Q8_0.gguf b/Qwen2.5-VL-3B-DocIndo.Q8_0.gguf new file mode 100644 index 0000000..39b1293 --- /dev/null +++ b/Qwen2.5-VL-3B-DocIndo.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc35a0232cbfc8ca98e3d52f394d9957c62426f583fbc07d0e550f870bb4b1aa +size 3285476224 diff --git a/Qwen2.5-VL-3B-DocIndo.f16.gguf b/Qwen2.5-VL-3B-DocIndo.f16.gguf new file mode 100644 index 0000000..ec4a2b7 --- /dev/null +++ b/Qwen2.5-VL-3B-DocIndo.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d70ae3661080c5a6e69af89b723874c529f9dc9cb14ee78bef4966089b556ee2 +size 6178317184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f700e36 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: danielsyahputra/Qwen2.5-VL-3B-DocIndo +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/danielsyahputra/Qwen2.5-VL-3B-DocIndo + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-VL-3B-DocIndo-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-VL-3B-DocIndo-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-DocIndo-GGUF/resolve/main/Qwen2.5-VL-3B-DocIndo.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-DocIndo-GGUF/resolve/main/Qwen2.5-VL-3B-DocIndo.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-DocIndo-GGUF/resolve/main/Qwen2.5-VL-3B-DocIndo.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-DocIndo-GGUF/resolve/main/Qwen2.5-VL-3B-DocIndo.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-DocIndo-GGUF/resolve/main/Qwen2.5-VL-3B-DocIndo.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-DocIndo-GGUF/resolve/main/Qwen2.5-VL-3B-DocIndo.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-DocIndo-GGUF/resolve/main/Qwen2.5-VL-3B-DocIndo.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-DocIndo-GGUF/resolve/main/Qwen2.5-VL-3B-DocIndo.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-DocIndo-GGUF/resolve/main/Qwen2.5-VL-3B-DocIndo.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-DocIndo-GGUF/resolve/main/Qwen2.5-VL-3B-DocIndo.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-DocIndo-GGUF/resolve/main/Qwen2.5-VL-3B-DocIndo.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-DocIndo-GGUF/resolve/main/Qwen2.5-VL-3B-DocIndo.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. + +