commit db3c89136ba5b170e3a15a06b6f7d14bdb97f0bf Author: ModelHub XC Date: Mon Jul 20 02:00:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5_VL_2B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c7342b9 --- /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_2B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5_VL_2B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5_VL_2B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5_VL_2B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5_VL_2B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5_VL_2B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5_VL_2B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5_VL_2B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5_VL_2B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5_VL_2B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5_VL_2B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5_VL_2B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5_VL_2B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5_VL_2B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5_VL_2B.IQ4_XS.gguf b/Qwen2.5_VL_2B.IQ4_XS.gguf new file mode 100644 index 0000000..53d16f9 --- /dev/null +++ b/Qwen2.5_VL_2B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc5c46d38dde41f933dc88d57bec8f406422b1d45fcac3ebf4f907372f0aa0e9 +size 1753184064 diff --git a/Qwen2.5_VL_2B.Q2_K.gguf b/Qwen2.5_VL_2B.Q2_K.gguf new file mode 100644 index 0000000..977de14 --- /dev/null +++ b/Qwen2.5_VL_2B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b4d7d3e696485d877c4a6d088f06241a114463a1761014e2d6b8ce73428fb81 +size 1274754880 diff --git a/Qwen2.5_VL_2B.Q3_K_L.gguf b/Qwen2.5_VL_2B.Q3_K_L.gguf new file mode 100644 index 0000000..2129b54 --- /dev/null +++ b/Qwen2.5_VL_2B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fe67441bf3f6b13397b3bafd9d36ecca2bf27f9350cde36a7178b12bb161413 +size 1707390784 diff --git a/Qwen2.5_VL_2B.Q3_K_M.gguf b/Qwen2.5_VL_2B.Q3_K_M.gguf new file mode 100644 index 0000000..5194457 --- /dev/null +++ b/Qwen2.5_VL_2B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb6d1034dbbb7a5a72023eba46847bf63baed6335176e13710f5b40204902262 +size 1590474560 diff --git a/Qwen2.5_VL_2B.Q3_K_S.gguf b/Qwen2.5_VL_2B.Q3_K_S.gguf new file mode 100644 index 0000000..da40661 --- /dev/null +++ b/Qwen2.5_VL_2B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deb3f18908280b9df62e4cae59eede4e98ca84305f030fc31a4f8550a08357fc +size 1454356288 diff --git a/Qwen2.5_VL_2B.Q4_K_M.gguf b/Qwen2.5_VL_2B.Q4_K_M.gguf new file mode 100644 index 0000000..5ae5006 --- /dev/null +++ b/Qwen2.5_VL_2B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d87611718d04485092d7ce8d6a45a5baeaf1a3d4796ec883209d6badfea85bab +size 1929901888 diff --git a/Qwen2.5_VL_2B.Q4_K_S.gguf b/Qwen2.5_VL_2B.Q4_K_S.gguf new file mode 100644 index 0000000..525e93a --- /dev/null +++ b/Qwen2.5_VL_2B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f4f593c4664cb4d616c01ff0bb17c717158d938c4fffc41311df129f68a0472 +size 1834383168 diff --git a/Qwen2.5_VL_2B.Q5_K_M.gguf b/Qwen2.5_VL_2B.Q5_K_M.gguf new file mode 100644 index 0000000..768187a --- /dev/null +++ b/Qwen2.5_VL_2B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:353f74fd19cdc66ddb09173cf00a4aaeb15189eafce76c5f3b528e97c74297ab +size 2224813888 diff --git a/Qwen2.5_VL_2B.Q5_K_S.gguf b/Qwen2.5_VL_2B.Q5_K_S.gguf new file mode 100644 index 0000000..0972a56 --- /dev/null +++ b/Qwen2.5_VL_2B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1edf88365bd37483c247263c39a3f8cabd7050343073cebb10c130052fbadb4f +size 2169665344 diff --git a/Qwen2.5_VL_2B.Q6_K.gguf b/Qwen2.5_VL_2B.Q6_K.gguf new file mode 100644 index 0000000..976f084 --- /dev/null +++ b/Qwen2.5_VL_2B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b6ef21bf0ff39a3f875dd00ede5db63c2ceb59c5f5c2e0c7306df97b4a7ccfb +size 2538157888 diff --git a/Qwen2.5_VL_2B.Q8_0.gguf b/Qwen2.5_VL_2B.Q8_0.gguf new file mode 100644 index 0000000..e897dc6 --- /dev/null +++ b/Qwen2.5_VL_2B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:590d6fd22806393e62da7372da1b086af773cee0bfdb63a2207eb9c5c662dd32 +size 3285475136 diff --git a/Qwen2.5_VL_2B.f16.gguf b/Qwen2.5_VL_2B.f16.gguf new file mode 100644 index 0000000..a3f0b28 --- /dev/null +++ b/Qwen2.5_VL_2B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:288118c76e96c290c575e1d83fc5a461a5d29759f87e5da25803d9d6190442bc +size 6178316096 diff --git a/Qwen2.5_VL_2B.mmproj-Q8_0.gguf b/Qwen2.5_VL_2B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..ef6829b --- /dev/null +++ b/Qwen2.5_VL_2B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a5154e8fd55b6d7f0f0064d7848c44f27cc6f98d9013906fe1ecdc19be0ffe0 +size 847768704 diff --git a/Qwen2.5_VL_2B.mmproj-f16.gguf b/Qwen2.5_VL_2B.mmproj-f16.gguf new file mode 100644 index 0000000..b01c6a0 --- /dev/null +++ b/Qwen2.5_VL_2B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45494cced51be9debf9095649cc459ce02da23cd1152fe7a76a7aa3e42c9647f +size 1338428544 diff --git a/README.md b/README.md new file mode 100644 index 0000000..944d50f --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: AbdouTobblaze/Qwen2.5_VL_2B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2_5_vl +--- +## About + + + + + + + + + +static quants of https://huggingface.co/AbdouTobblaze/Qwen2.5_VL_2B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5_VL_2B-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_2B-GGUF/resolve/main/Qwen2.5_VL_2B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5_VL_2B-GGUF/resolve/main/Qwen2.5_VL_2B.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5_VL_2B-GGUF/resolve/main/Qwen2.5_VL_2B.mmproj-f16.gguf) | mmproj-f16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5_VL_2B-GGUF/resolve/main/Qwen2.5_VL_2B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5_VL_2B-GGUF/resolve/main/Qwen2.5_VL_2B.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5_VL_2B-GGUF/resolve/main/Qwen2.5_VL_2B.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5_VL_2B-GGUF/resolve/main/Qwen2.5_VL_2B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5_VL_2B-GGUF/resolve/main/Qwen2.5_VL_2B.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5_VL_2B-GGUF/resolve/main/Qwen2.5_VL_2B.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5_VL_2B-GGUF/resolve/main/Qwen2.5_VL_2B.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5_VL_2B-GGUF/resolve/main/Qwen2.5_VL_2B.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5_VL_2B-GGUF/resolve/main/Qwen2.5_VL_2B.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5_VL_2B-GGUF/resolve/main/Qwen2.5_VL_2B.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5_VL_2B-GGUF/resolve/main/Qwen2.5_VL_2B.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. + +