commit d404210a9331bfb8e525474a6638e3c5e621796c Author: ModelHub XC Date: Wed Jun 10 08:19:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/VLAA-Thinker-Qwen2.5VL-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b8da42a --- /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 +VLAA-Thinker-Qwen2.5VL-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2.5VL-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2.5VL-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2.5VL-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2.5VL-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2.5VL-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2.5VL-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2.5VL-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2.5VL-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2.5VL-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2.5VL-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2.5VL-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2.5VL-3B.mmproj-fp16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..fd94c81 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: UCSC-VLAA/VLAA-Thinker-Qwen2.5VL-3B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/UCSC-VLAA/VLAA-Thinker-Qwen2.5VL-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#VLAA-Thinker-Qwen2.5VL-3B-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/VLAA-Thinker-Qwen2.5VL-3B-GGUF/resolve/main/VLAA-Thinker-Qwen2.5VL-3B.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2.5VL-3B-GGUF/resolve/main/VLAA-Thinker-Qwen2.5VL-3B.mmproj-fp16.gguf) | mmproj-fp16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2.5VL-3B-GGUF/resolve/main/VLAA-Thinker-Qwen2.5VL-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2.5VL-3B-GGUF/resolve/main/VLAA-Thinker-Qwen2.5VL-3B.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2.5VL-3B-GGUF/resolve/main/VLAA-Thinker-Qwen2.5VL-3B.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2.5VL-3B-GGUF/resolve/main/VLAA-Thinker-Qwen2.5VL-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2.5VL-3B-GGUF/resolve/main/VLAA-Thinker-Qwen2.5VL-3B.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2.5VL-3B-GGUF/resolve/main/VLAA-Thinker-Qwen2.5VL-3B.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2.5VL-3B-GGUF/resolve/main/VLAA-Thinker-Qwen2.5VL-3B.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2.5VL-3B-GGUF/resolve/main/VLAA-Thinker-Qwen2.5VL-3B.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2.5VL-3B-GGUF/resolve/main/VLAA-Thinker-Qwen2.5VL-3B.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2.5VL-3B-GGUF/resolve/main/VLAA-Thinker-Qwen2.5VL-3B.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2.5VL-3B-GGUF/resolve/main/VLAA-Thinker-Qwen2.5VL-3B.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. + + diff --git a/VLAA-Thinker-Qwen2.5VL-3B.IQ4_XS.gguf b/VLAA-Thinker-Qwen2.5VL-3B.IQ4_XS.gguf new file mode 100644 index 0000000..b2a1c09 --- /dev/null +++ b/VLAA-Thinker-Qwen2.5VL-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e1e45d179830328d66c1e38e21744f54319ea3c60fd52e61bafa904c2c864d8 +size 1753185152 diff --git a/VLAA-Thinker-Qwen2.5VL-3B.Q2_K.gguf b/VLAA-Thinker-Qwen2.5VL-3B.Q2_K.gguf new file mode 100644 index 0000000..f3356cb --- /dev/null +++ b/VLAA-Thinker-Qwen2.5VL-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1736eecc8830dd2cbfbef5e096064121272d6b13c2aebf857dc9564e7e2100b7 +size 1274755968 diff --git a/VLAA-Thinker-Qwen2.5VL-3B.Q3_K_L.gguf b/VLAA-Thinker-Qwen2.5VL-3B.Q3_K_L.gguf new file mode 100644 index 0000000..62333d2 --- /dev/null +++ b/VLAA-Thinker-Qwen2.5VL-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd1ae5948fcfb3f5d14158fafe3dc281cf8879658924a987169d728b078b4222 +size 1707391872 diff --git a/VLAA-Thinker-Qwen2.5VL-3B.Q3_K_M.gguf b/VLAA-Thinker-Qwen2.5VL-3B.Q3_K_M.gguf new file mode 100644 index 0000000..d918c01 --- /dev/null +++ b/VLAA-Thinker-Qwen2.5VL-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e25ab47610655deb65e758cc54acfb23bc9be91d628e98b08fb0223b8cbfefed +size 1590475648 diff --git a/VLAA-Thinker-Qwen2.5VL-3B.Q3_K_S.gguf b/VLAA-Thinker-Qwen2.5VL-3B.Q3_K_S.gguf new file mode 100644 index 0000000..92d6100 --- /dev/null +++ b/VLAA-Thinker-Qwen2.5VL-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02bb77f9a9e8246d36b6dac4348e1435e22d4c582cfc7c154ecf3fb8f4be48b8 +size 1454357376 diff --git a/VLAA-Thinker-Qwen2.5VL-3B.Q4_K_M.gguf b/VLAA-Thinker-Qwen2.5VL-3B.Q4_K_M.gguf new file mode 100644 index 0000000..3529961 --- /dev/null +++ b/VLAA-Thinker-Qwen2.5VL-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dedffe7c519efeb390650ea6a8557a14723fcb74ac8e5308916b7a2efb3578b +size 1929902976 diff --git a/VLAA-Thinker-Qwen2.5VL-3B.Q4_K_S.gguf b/VLAA-Thinker-Qwen2.5VL-3B.Q4_K_S.gguf new file mode 100644 index 0000000..2bc59a6 --- /dev/null +++ b/VLAA-Thinker-Qwen2.5VL-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:248835854a5a0dc9c059cae152c23d25dbb341f97fd33bd778a6833e0616a5ea +size 1834384256 diff --git a/VLAA-Thinker-Qwen2.5VL-3B.Q5_K_M.gguf b/VLAA-Thinker-Qwen2.5VL-3B.Q5_K_M.gguf new file mode 100644 index 0000000..2bedcc7 --- /dev/null +++ b/VLAA-Thinker-Qwen2.5VL-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c11d6ede288d72cf8cbebd390a557546358d8f277ec2bf438f582e7b4b9728b +size 2224814976 diff --git a/VLAA-Thinker-Qwen2.5VL-3B.Q5_K_S.gguf b/VLAA-Thinker-Qwen2.5VL-3B.Q5_K_S.gguf new file mode 100644 index 0000000..dd4f009 --- /dev/null +++ b/VLAA-Thinker-Qwen2.5VL-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd1501781a5e34c078cc112e1d48be9e0c3c064fc84e4e9ed3a0d4a590b600a0 +size 2169666432 diff --git a/VLAA-Thinker-Qwen2.5VL-3B.Q6_K.gguf b/VLAA-Thinker-Qwen2.5VL-3B.Q6_K.gguf new file mode 100644 index 0000000..9188759 --- /dev/null +++ b/VLAA-Thinker-Qwen2.5VL-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b388707a1a5476eb2f8c31a809d4c8aa1358a18ac3828b1ede2ad06c4d34c15 +size 2538158976 diff --git a/VLAA-Thinker-Qwen2.5VL-3B.Q8_0.gguf b/VLAA-Thinker-Qwen2.5VL-3B.Q8_0.gguf new file mode 100644 index 0000000..fe7126e --- /dev/null +++ b/VLAA-Thinker-Qwen2.5VL-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccc3cb313c8fb273e96850f407fc1007d3cd01c3fc8d3f38a02e0d2e0d466215 +size 3285476224 diff --git a/VLAA-Thinker-Qwen2.5VL-3B.f16.gguf b/VLAA-Thinker-Qwen2.5VL-3B.f16.gguf new file mode 100644 index 0000000..05b4f2d --- /dev/null +++ b/VLAA-Thinker-Qwen2.5VL-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:551a62e67bcef15852988861076c366a19afc5cc940ec590ca90ec9ce83db2e7 +size 6178317184 diff --git a/VLAA-Thinker-Qwen2.5VL-3B.mmproj-fp16.gguf b/VLAA-Thinker-Qwen2.5VL-3B.mmproj-fp16.gguf new file mode 100644 index 0000000..556eb1e --- /dev/null +++ b/VLAA-Thinker-Qwen2.5VL-3B.mmproj-fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49fac55b2e9ee434868e97eef9f9bfdbccf80cd271ebf8eef8f7dfc0f17822a7 +size 1338428544