commit 6db282e07ed71647174e88fefabae08db15b4566 Author: ModelHub XC Date: Sun Jul 19 17:49:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-VL-3B-OCR-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..68574f8 --- /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 +Qwen2.5-VL-3B-OCR.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-OCR.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-OCR.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-OCR.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-OCR.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-OCR.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-OCR.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-OCR.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-OCR.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-OCR.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-OCR.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-OCR.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-OCR.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-OCR.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-VL-3B-OCR.IQ4_XS.gguf b/Qwen2.5-VL-3B-OCR.IQ4_XS.gguf new file mode 100644 index 0000000..02421e2 --- /dev/null +++ b/Qwen2.5-VL-3B-OCR.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb4032e32a4b0a24b018712440cb160dfd0108c769503973a6f9090d42657cb6 +size 1753183648 diff --git a/Qwen2.5-VL-3B-OCR.Q2_K.gguf b/Qwen2.5-VL-3B-OCR.Q2_K.gguf new file mode 100644 index 0000000..e1ead3b --- /dev/null +++ b/Qwen2.5-VL-3B-OCR.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e367ae9a7755643cafa3ef58135d762867fd4fc8c51470708cbd602fc918bc6a +size 1274754464 diff --git a/Qwen2.5-VL-3B-OCR.Q3_K_L.gguf b/Qwen2.5-VL-3B-OCR.Q3_K_L.gguf new file mode 100644 index 0000000..2c35d6d --- /dev/null +++ b/Qwen2.5-VL-3B-OCR.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25541c4c463752e7feef3e4bfb68e6b7275d5604811c0ff3cd4bc7644da32de5 +size 1707390368 diff --git a/Qwen2.5-VL-3B-OCR.Q3_K_M.gguf b/Qwen2.5-VL-3B-OCR.Q3_K_M.gguf new file mode 100644 index 0000000..89ce451 --- /dev/null +++ b/Qwen2.5-VL-3B-OCR.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83fc9376431f27055a6e1801c4588e70e0764623ce3829aa0630b972bda10eea +size 1590474144 diff --git a/Qwen2.5-VL-3B-OCR.Q3_K_S.gguf b/Qwen2.5-VL-3B-OCR.Q3_K_S.gguf new file mode 100644 index 0000000..ffdbc7f --- /dev/null +++ b/Qwen2.5-VL-3B-OCR.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ecd5d4b92dc2b52c5057ee55a142e7f32f9539dc2f2b6af0940cb5cda5b5278 +size 1454355872 diff --git a/Qwen2.5-VL-3B-OCR.Q4_K_M.gguf b/Qwen2.5-VL-3B-OCR.Q4_K_M.gguf new file mode 100644 index 0000000..e82b763 --- /dev/null +++ b/Qwen2.5-VL-3B-OCR.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5934c2f8a9906e7614220ededd2b80250498d26cb26bc3542231c893861fd2de +size 1929901472 diff --git a/Qwen2.5-VL-3B-OCR.Q4_K_S.gguf b/Qwen2.5-VL-3B-OCR.Q4_K_S.gguf new file mode 100644 index 0000000..1c87fcf --- /dev/null +++ b/Qwen2.5-VL-3B-OCR.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:674e8cefa83dadea61856240380c0313ec2acdcb57cf68ec62acef21f500ff17 +size 1834382752 diff --git a/Qwen2.5-VL-3B-OCR.Q5_K_M.gguf b/Qwen2.5-VL-3B-OCR.Q5_K_M.gguf new file mode 100644 index 0000000..f0200db --- /dev/null +++ b/Qwen2.5-VL-3B-OCR.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33d3021da5f6fbb34151c6bdef98f98b5d68c6d20c30eabdf64c9f94d1430413 +size 2224813472 diff --git a/Qwen2.5-VL-3B-OCR.Q5_K_S.gguf b/Qwen2.5-VL-3B-OCR.Q5_K_S.gguf new file mode 100644 index 0000000..6926488 --- /dev/null +++ b/Qwen2.5-VL-3B-OCR.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:254d30d2d1b8652208dae53b5d27cf944da3ade103a50d48f3fa3dc00f7849a7 +size 2169664928 diff --git a/Qwen2.5-VL-3B-OCR.Q6_K.gguf b/Qwen2.5-VL-3B-OCR.Q6_K.gguf new file mode 100644 index 0000000..048a87e --- /dev/null +++ b/Qwen2.5-VL-3B-OCR.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10588ffc033034956a4ff43b74d6243c672f6f55964d88061a64694dc1509c84 +size 2538157472 diff --git a/Qwen2.5-VL-3B-OCR.Q8_0.gguf b/Qwen2.5-VL-3B-OCR.Q8_0.gguf new file mode 100644 index 0000000..9860526 --- /dev/null +++ b/Qwen2.5-VL-3B-OCR.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaf6583d62d506543fec83a1a7b7bd750601075f035e2cca862a957d3b0a2ee6 +size 3285474720 diff --git a/Qwen2.5-VL-3B-OCR.f16.gguf b/Qwen2.5-VL-3B-OCR.f16.gguf new file mode 100644 index 0000000..971f585 --- /dev/null +++ b/Qwen2.5-VL-3B-OCR.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7747593905d3975aaf73761c13e36c0d26e2cf2854fefd17b4c9723ecdc8d724 +size 6178315680 diff --git a/Qwen2.5-VL-3B-OCR.mmproj-Q8_0.gguf b/Qwen2.5-VL-3B-OCR.mmproj-Q8_0.gguf new file mode 100644 index 0000000..8479881 --- /dev/null +++ b/Qwen2.5-VL-3B-OCR.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:549e54665d71a0847eae04e65749163109385075e7f030c4244f1e17643eaf32 +size 847768256 diff --git a/Qwen2.5-VL-3B-OCR.mmproj-f16.gguf b/Qwen2.5-VL-3B-OCR.mmproj-f16.gguf new file mode 100644 index 0000000..d4415ad --- /dev/null +++ b/Qwen2.5-VL-3B-OCR.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cd73b225947a6aa0631501a25ce3aa45e6ec8a6337ff017e4d23d5e61c3b24d +size 1338428096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5c0a3ec --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: mikelainsa/Qwen2.5-VL-3B-OCR +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/mikelainsa/Qwen2.5-VL-3B-OCR + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-VL-3B-OCR-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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-OCR-GGUF/resolve/main/Qwen2.5-VL-3B-OCR.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-OCR-GGUF/resolve/main/Qwen2.5-VL-3B-OCR.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-OCR-GGUF/resolve/main/Qwen2.5-VL-3B-OCR.mmproj-f16.gguf) | mmproj-f16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-OCR-GGUF/resolve/main/Qwen2.5-VL-3B-OCR.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-OCR-GGUF/resolve/main/Qwen2.5-VL-3B-OCR.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-OCR-GGUF/resolve/main/Qwen2.5-VL-3B-OCR.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-OCR-GGUF/resolve/main/Qwen2.5-VL-3B-OCR.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-OCR-GGUF/resolve/main/Qwen2.5-VL-3B-OCR.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-OCR-GGUF/resolve/main/Qwen2.5-VL-3B-OCR.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-OCR-GGUF/resolve/main/Qwen2.5-VL-3B-OCR.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-OCR-GGUF/resolve/main/Qwen2.5-VL-3B-OCR.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-OCR-GGUF/resolve/main/Qwen2.5-VL-3B-OCR.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-OCR-GGUF/resolve/main/Qwen2.5-VL-3B-OCR.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-OCR-GGUF/resolve/main/Qwen2.5-VL-3B-OCR.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. + +