commit 72d309bf2dc77566dda3f36c062f75b8f928ebea Author: ModelHub XC Date: Sun May 10 08:22:08 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GRIT-20-Qwen2.5-VL-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d3c8825 --- /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 +GRIT-20-Qwen2.5-VL-3B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GRIT-20-Qwen2.5-VL-3B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +GRIT-20-Qwen2.5-VL-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GRIT-20-Qwen2.5-VL-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GRIT-20-Qwen2.5-VL-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GRIT-20-Qwen2.5-VL-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRIT-20-Qwen2.5-VL-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRIT-20-Qwen2.5-VL-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRIT-20-Qwen2.5-VL-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRIT-20-Qwen2.5-VL-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRIT-20-Qwen2.5-VL-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRIT-20-Qwen2.5-VL-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GRIT-20-Qwen2.5-VL-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GRIT-20-Qwen2.5-VL-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GRIT-20-Qwen2.5-VL-3B.IQ4_XS.gguf b/GRIT-20-Qwen2.5-VL-3B.IQ4_XS.gguf new file mode 100644 index 0000000..cce45fb --- /dev/null +++ b/GRIT-20-Qwen2.5-VL-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ca545bc6c6e94042ec31ee3a7d538c676ffba50e65b3d3eae37b259749b213a +size 1753183712 diff --git a/GRIT-20-Qwen2.5-VL-3B.Q2_K.gguf b/GRIT-20-Qwen2.5-VL-3B.Q2_K.gguf new file mode 100644 index 0000000..ac9d48c --- /dev/null +++ b/GRIT-20-Qwen2.5-VL-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f07acd4a49c17ce99da3883df389ea253103ed412ea7395dcf12d17f4767f9f6 +size 1274754528 diff --git a/GRIT-20-Qwen2.5-VL-3B.Q3_K_L.gguf b/GRIT-20-Qwen2.5-VL-3B.Q3_K_L.gguf new file mode 100644 index 0000000..9e97646 --- /dev/null +++ b/GRIT-20-Qwen2.5-VL-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82a2560b3c9943af8fa91f5ad523fb93bc5b94b67fbd321da9ee51477d89ae7a +size 1707390432 diff --git a/GRIT-20-Qwen2.5-VL-3B.Q3_K_M.gguf b/GRIT-20-Qwen2.5-VL-3B.Q3_K_M.gguf new file mode 100644 index 0000000..f1528e4 --- /dev/null +++ b/GRIT-20-Qwen2.5-VL-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fdd91dc2ab519b5b2abd0c4a1abe31e894de4467c265cba90a02c2837cd0aea +size 1590474208 diff --git a/GRIT-20-Qwen2.5-VL-3B.Q3_K_S.gguf b/GRIT-20-Qwen2.5-VL-3B.Q3_K_S.gguf new file mode 100644 index 0000000..d2eaf6e --- /dev/null +++ b/GRIT-20-Qwen2.5-VL-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc208ba968fa13ac0a465794775d2e8ab1be708b8515c70bccdbab8df2a6d981 +size 1454355936 diff --git a/GRIT-20-Qwen2.5-VL-3B.Q4_K_M.gguf b/GRIT-20-Qwen2.5-VL-3B.Q4_K_M.gguf new file mode 100644 index 0000000..b16b569 --- /dev/null +++ b/GRIT-20-Qwen2.5-VL-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e94a29cf217dfb124065b1495d7befde85e3694aec9a432fdcb42c04dee39f1e +size 1929901536 diff --git a/GRIT-20-Qwen2.5-VL-3B.Q4_K_S.gguf b/GRIT-20-Qwen2.5-VL-3B.Q4_K_S.gguf new file mode 100644 index 0000000..a865cf1 --- /dev/null +++ b/GRIT-20-Qwen2.5-VL-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7f97374ea6bbd465c5895660b09ad38a4bfc85f79f6e8ff16271f7c04be1a25 +size 1834382816 diff --git a/GRIT-20-Qwen2.5-VL-3B.Q5_K_M.gguf b/GRIT-20-Qwen2.5-VL-3B.Q5_K_M.gguf new file mode 100644 index 0000000..828518a --- /dev/null +++ b/GRIT-20-Qwen2.5-VL-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c38a576d4d72808c81f50d6a97bd8bd8bfcbfc9022f51aaf0bc7e4a548c0dfe5 +size 2224813536 diff --git a/GRIT-20-Qwen2.5-VL-3B.Q5_K_S.gguf b/GRIT-20-Qwen2.5-VL-3B.Q5_K_S.gguf new file mode 100644 index 0000000..e9f09a5 --- /dev/null +++ b/GRIT-20-Qwen2.5-VL-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11f830decabf5595f216199279bc9e226c553bfdc1d5b856abc7cb98946e1733 +size 2169664992 diff --git a/GRIT-20-Qwen2.5-VL-3B.Q6_K.gguf b/GRIT-20-Qwen2.5-VL-3B.Q6_K.gguf new file mode 100644 index 0000000..0a32e16 --- /dev/null +++ b/GRIT-20-Qwen2.5-VL-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ea68d4bd5a5b53e422cff3b17f4480d21164ff97ba00218726c6ed73c5a16d4 +size 2538157536 diff --git a/GRIT-20-Qwen2.5-VL-3B.Q8_0.gguf b/GRIT-20-Qwen2.5-VL-3B.Q8_0.gguf new file mode 100644 index 0000000..8337612 --- /dev/null +++ b/GRIT-20-Qwen2.5-VL-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e93ae356e87c753335a90c49510c17157f2bb9852674fe7e1d6d79419165a5e +size 3285474784 diff --git a/GRIT-20-Qwen2.5-VL-3B.f16.gguf b/GRIT-20-Qwen2.5-VL-3B.f16.gguf new file mode 100644 index 0000000..ac14191 --- /dev/null +++ b/GRIT-20-Qwen2.5-VL-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96c8483a100f0f09f1d75d57b83f5acf0d839854666a580e70f412b190d2cead +size 6178315744 diff --git a/GRIT-20-Qwen2.5-VL-3B.mmproj-Q8_0.gguf b/GRIT-20-Qwen2.5-VL-3B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..88bcb6f --- /dev/null +++ b/GRIT-20-Qwen2.5-VL-3B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:145affda6fa9dc4373bc9f96f626de89ebaf5220040c718963b86b1208eb1ab2 +size 844757760 diff --git a/GRIT-20-Qwen2.5-VL-3B.mmproj-f16.gguf b/GRIT-20-Qwen2.5-VL-3B.mmproj-f16.gguf new file mode 100644 index 0000000..c1d36fb --- /dev/null +++ b/GRIT-20-Qwen2.5-VL-3B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b117f2bdd01824a4508ea448fa1cf6905ff9a603f8b9aeb142b3116d25dedebe +size 1338428160 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0664ac9 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: yfan1997/GRIT-20-Qwen2.5-VL-3B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/yfan1997/GRIT-20-Qwen2.5-VL-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GRIT-20-Qwen2.5-VL-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/GRIT-20-Qwen2.5-VL-3B-GGUF/resolve/main/GRIT-20-Qwen2.5-VL-3B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/GRIT-20-Qwen2.5-VL-3B-GGUF/resolve/main/GRIT-20-Qwen2.5-VL-3B.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/GRIT-20-Qwen2.5-VL-3B-GGUF/resolve/main/GRIT-20-Qwen2.5-VL-3B.mmproj-f16.gguf) | mmproj-f16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/GRIT-20-Qwen2.5-VL-3B-GGUF/resolve/main/GRIT-20-Qwen2.5-VL-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/GRIT-20-Qwen2.5-VL-3B-GGUF/resolve/main/GRIT-20-Qwen2.5-VL-3B.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GRIT-20-Qwen2.5-VL-3B-GGUF/resolve/main/GRIT-20-Qwen2.5-VL-3B.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/GRIT-20-Qwen2.5-VL-3B-GGUF/resolve/main/GRIT-20-Qwen2.5-VL-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/GRIT-20-Qwen2.5-VL-3B-GGUF/resolve/main/GRIT-20-Qwen2.5-VL-3B.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRIT-20-Qwen2.5-VL-3B-GGUF/resolve/main/GRIT-20-Qwen2.5-VL-3B.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRIT-20-Qwen2.5-VL-3B-GGUF/resolve/main/GRIT-20-Qwen2.5-VL-3B.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/GRIT-20-Qwen2.5-VL-3B-GGUF/resolve/main/GRIT-20-Qwen2.5-VL-3B.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/GRIT-20-Qwen2.5-VL-3B-GGUF/resolve/main/GRIT-20-Qwen2.5-VL-3B.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GRIT-20-Qwen2.5-VL-3B-GGUF/resolve/main/GRIT-20-Qwen2.5-VL-3B.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GRIT-20-Qwen2.5-VL-3B-GGUF/resolve/main/GRIT-20-Qwen2.5-VL-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. + +