commit 16c5b540be779c8a55e60f582329d5682cda8f37 Author: ModelHub XC Date: Wed Jun 17 17:52:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..31b3da0 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-S1.1-3B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5VL-S1.1-3B.i1-IQ1_M.gguf b/Qwen2.5VL-S1.1-3B.i1-IQ1_M.gguf new file mode 100644 index 0000000..0809973 --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e633e81362c7a97fd8f88acb6427090e1316d6420e0d814c13a79890ec20154 +size 952128992 diff --git a/Qwen2.5VL-S1.1-3B.i1-IQ1_S.gguf b/Qwen2.5VL-S1.1-3B.i1-IQ1_S.gguf new file mode 100644 index 0000000..1225698 --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3720dca935aa21974fa9679c7d17b7a57a9d788777f38deb7288baa3c12e123 +size 893195744 diff --git a/Qwen2.5VL-S1.1-3B.i1-IQ2_M.gguf b/Qwen2.5VL-S1.1-3B.i1-IQ2_M.gguf new file mode 100644 index 0000000..77fe645 --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06d0ed581dcbf04e224b4e9d759aa619448e4ce0296c15a7325e3f3a77e250bd +size 1274220000 diff --git a/Qwen2.5VL-S1.1-3B.i1-IQ2_S.gguf b/Qwen2.5VL-S1.1-3B.i1-IQ2_S.gguf new file mode 100644 index 0000000..c73154f --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad50aa808cf6edb7a5468240458f4864c23fe33887b08de2a146407069c536f9 +size 1195642336 diff --git a/Qwen2.5VL-S1.1-3B.i1-IQ2_XS.gguf b/Qwen2.5VL-S1.1-3B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..a0530d1 --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef60eeabce6ad9c3a2122a2a0bd1632293dadef91cfbdacc71fd5a04294b1ad0 +size 1133647328 diff --git a/Qwen2.5VL-S1.1-3B.i1-IQ2_XXS.gguf b/Qwen2.5VL-S1.1-3B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..fd0f1ed --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:183299e53bfffb762bf638de37f2bb049eae7d72a86afdde320baa8076c7597a +size 1050351072 diff --git a/Qwen2.5VL-S1.1-3B.i1-IQ3_M.gguf b/Qwen2.5VL-S1.1-3B.i1-IQ3_M.gguf new file mode 100644 index 0000000..0d8dc3a --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c332dae766e0d334568ea883ec393ccfe5dad9771ec236124cd769e7bee7a8df +size 1622599136 diff --git a/Qwen2.5VL-S1.1-3B.i1-IQ3_S.gguf b/Qwen2.5VL-S1.1-3B.i1-IQ3_S.gguf new file mode 100644 index 0000000..4d40131 --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b255be1ca2f419b9cb04d69ddd0657401b3e84ba0803bdb112ffd975c874513e +size 1590568416 diff --git a/Qwen2.5VL-S1.1-3B.i1-IQ3_XS.gguf b/Qwen2.5VL-S1.1-3B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..6f8779d --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6eba458f2c920b662bcb4fa7bb84c6e03eba1576862d61366b28b27813c595ab +size 1525540320 diff --git a/Qwen2.5VL-S1.1-3B.i1-IQ3_XXS.gguf b/Qwen2.5VL-S1.1-3B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..69b1d09 --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0e780435155e239f13e54d0cc1040bf8e85c8fa9d11b18bd968b3571d9203e5 +size 1416531424 diff --git a/Qwen2.5VL-S1.1-3B.i1-IQ4_NL.gguf b/Qwen2.5VL-S1.1-3B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..fe1b1f0 --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcbbbb146499a4c05ad13cf297a68a7d2674a1e93c597028e1ea11377baf509c +size 2000240096 diff --git a/Qwen2.5VL-S1.1-3B.i1-IQ4_XS.gguf b/Qwen2.5VL-S1.1-3B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..1f7b8ec --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:058f0b6ff9578e79f944c687f8a26d3aabb114811e1e9a37e2898813469bb0ee +size 1904401888 diff --git a/Qwen2.5VL-S1.1-3B.i1-Q2_K.gguf b/Qwen2.5VL-S1.1-3B.i1-Q2_K.gguf new file mode 100644 index 0000000..3b16ec4 --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc69ab473034e4d86412085bf2d9125af68bd0be676bfe327484afe37558a7f2 +size 1376857568 diff --git a/Qwen2.5VL-S1.1-3B.i1-Q2_K_S.gguf b/Qwen2.5VL-S1.1-3B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..8f6f388 --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bf94202b3c59bc9b8c8e31b6cea8ba308b97144de6cd18ee1fdaef45a5b733d +size 1300229600 diff --git a/Qwen2.5VL-S1.1-3B.i1-Q3_K_L.gguf b/Qwen2.5VL-S1.1-3B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..8ae85ab --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afd2f8789cfa51e25e0c80a3e383983a0eb85c831729d6e6c9bad54852b8cff8 +size 1841096160 diff --git a/Qwen2.5VL-S1.1-3B.i1-Q3_K_M.gguf b/Qwen2.5VL-S1.1-3B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..6e1fc4d --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2adf90b611bab5a75ccd0ca9b0077cbc912279720d569da9902cd0957aaf85e9 +size 1724179936 diff --git a/Qwen2.5VL-S1.1-3B.i1-Q3_K_S.gguf b/Qwen2.5VL-S1.1-3B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..6c37387 --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4820dede6f214cfc3176f69393734176ff6dd42904a57d7c29dd8c5e5cc07d9e +size 1588061664 diff --git a/Qwen2.5VL-S1.1-3B.i1-Q4_0.gguf b/Qwen2.5VL-S1.1-3B.i1-Q4_0.gguf new file mode 100644 index 0000000..47d265c --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55efe885c8fa4f4109f172831ecefef4bcf814ed091f6b07946ce60fe1380c40 +size 2003516896 diff --git a/Qwen2.5VL-S1.1-3B.i1-Q4_1.gguf b/Qwen2.5VL-S1.1-3B.i1-Q4_1.gguf new file mode 100644 index 0000000..8d614d9 --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8fd8fa27c30d0d4ab75e933b8137a6a57af3658f12e1b50bb059673fd615aba +size 2190736864 diff --git a/Qwen2.5VL-S1.1-3B.i1-Q4_K_M.gguf b/Qwen2.5VL-S1.1-3B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..bd0ff22 --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9b0b4ccffc072de35b9477d96fc9cf484bb30c434d31bf0b83e8bfde9ca9ce4 +size 2104933856 diff --git a/Qwen2.5VL-S1.1-3B.i1-Q4_K_S.gguf b/Qwen2.5VL-S1.1-3B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..f25f92c --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2effb1239f18b7a065096c61cc54525bb77cc55e1fd8631359b678c6424616b4 +size 2009415136 diff --git a/Qwen2.5VL-S1.1-3B.i1-Q5_K_M.gguf b/Qwen2.5VL-S1.1-3B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..cc98ac9 --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ad7215959fbbb8f1899178dcf83d753388637b2ac072dc33fb037cb1e5a0a1f +size 2438741472 diff --git a/Qwen2.5VL-S1.1-3B.i1-Q5_K_S.gguf b/Qwen2.5VL-S1.1-3B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..6048ebe --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca5695ab071a7e8723de948b15c10423e0cdedd93159d5eacac70cc0621e4b76 +size 2383592928 diff --git a/Qwen2.5VL-S1.1-3B.i1-Q6_K.gguf b/Qwen2.5VL-S1.1-3B.i1-Q6_K.gguf new file mode 100644 index 0000000..a27890d --- /dev/null +++ b/Qwen2.5VL-S1.1-3B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c11ca08b7d14757ca59c2d89ac1792d8b25482e3a699ae21a5025707783f95c +size 2793412064 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4e69d41 --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: ZhaoJingfu/Qwen2.5VL-S1.1-3B +language: +- en +library_name: transformers +model_name: s1-20250221_173316 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- sft +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/ZhaoJingfu/Qwen2.5VL-S1.1-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5VL-S1.1-3B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-GGUF + +**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-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/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-IQ1_M.gguf) | i1-IQ1_M | 1.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-IQ2_M.gguf) | i1-IQ2_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.7 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-IQ3_S.gguf) | i1-IQ3_S | 1.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.1 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-Q4_0.gguf) | i1-Q4_0 | 2.1 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.1 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-Q4_1.gguf) | i1-Q4_1 | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-S1.1-3B-i1-GGUF/resolve/main/Qwen2.5VL-S1.1-3B.i1-Q6_K.gguf) | i1-Q6_K | 2.9 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..6ace5dd --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25292a5939707104c4b352c09c4ac2ddd25215f424b7ce306cb835581234566d +size 3362977