commit dad1358ab9702390e740576cfc4658cfabfafb14 Author: ModelHub XC Date: Sun Apr 12 13:18:08 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dda1add --- /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 +Qwen3-VisionCaption-2B-Thinking.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-Thinking.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-IQ1_M.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-IQ1_M.gguf new file mode 100644 index 0000000..5536441 --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a79c7ab2a793ac298fb254de1d6378651c2409ace8214109cbec43ca2b029ea9 +size 543796000 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-IQ1_S.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-IQ1_S.gguf new file mode 100644 index 0000000..c3b5f4f --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c56279799882845e6637ad0631ed381e067e555d2d5670088d04d38be39c2f0 +size 515779360 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-IQ2_M.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-IQ2_M.gguf new file mode 100644 index 0000000..2ee555d --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c33be6ff939ef015eeb8281d50f99b50801c742edecd39f25f6617edc500849c +size 695184160 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-IQ2_S.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-IQ2_S.gguf new file mode 100644 index 0000000..7a10fe1 --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91a4678a7d82069818e1256917e499ab20642794e21a85a454a39d0b86c6fdce +size 657828640 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-IQ2_XS.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-IQ2_XS.gguf new file mode 100644 index 0000000..24a6f38 --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c20de1e0b8b110ee0a075fe85c47b8624a66cd8a182b30e5a18a182e5337ff6b +size 631515936 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-IQ2_XXS.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..4f36a09 --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dcd81d86e6d332dab8ec16b3059e6f9f1673e5e54cbe5396284e60201a16887 +size 590490400 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-IQ3_M.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-IQ3_M.gguf new file mode 100644 index 0000000..5d3d75f --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f0ea6d41141e6386d65ecf570ca15084d41faca139a870b99e01c32d466ff92 +size 895664928 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-IQ3_S.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-IQ3_S.gguf new file mode 100644 index 0000000..bf8788d --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6d0cf3c11f9e4b2b4bd46e236d9779a79d646661a0f4652a98ae950597cda94 +size 867255072 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-IQ3_XS.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-IQ3_XS.gguf new file mode 100644 index 0000000..11b1929 --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9948ba6bb7880419750a652c1c8c5bbf9afbe7380caa01500899ef758ce34742 +size 834224928 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-IQ3_XXS.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..a39fb72 --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1792f76f7b37df73ff46cc7d9f0a2201f7d28ef362656f0f983a0207b1835484 +size 754363168 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-IQ4_NL.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-IQ4_NL.gguf new file mode 100644 index 0000000..61f27cd --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d43937f4aa346398a8062aa8ea0fb960ec89b3035dc47234fbc4a3a2267b172 +size 1054425888 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-IQ4_XS.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-IQ4_XS.gguf new file mode 100644 index 0000000..ea777f5 --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:affc9ef0f5545c292591c682b4c24b18d9303a98a2f8e77138b684f73fbf8030 +size 1010385696 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-Q2_K.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-Q2_K.gguf new file mode 100644 index 0000000..153d591 --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:081f30eda2f50174aa5c700a1977f36fec21e2d9c01b08fc31bca1958beb6297 +size 777798432 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-Q2_K_S.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-Q2_K_S.gguf new file mode 100644 index 0000000..375f09d --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc6dde89443d49be45255aaf15381a8c1a209ef6659824610107edffa9ccc063 +size 732971808 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-Q3_K_L.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-Q3_K_L.gguf new file mode 100644 index 0000000..fd3226a --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28057b241cb880184118c72c1c42b6aa0914a6f2366205520f21cdfd4eddf303 +size 1003504416 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-Q3_K_M.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-Q3_K_M.gguf new file mode 100644 index 0000000..640d050 --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c8fbb33adbe8e5c791a2b819d2c32bd5f1d4f46de3b97b370336a901d33eb7f +size 939541280 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-Q3_K_S.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-Q3_K_S.gguf new file mode 100644 index 0000000..3cf70b5 --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8c4c85f02ad0e6b5bedb024ab8403791ae3d441f0c9f2a8f7558b6978ed7e67 +size 867255072 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-Q4_0.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-Q4_0.gguf new file mode 100644 index 0000000..93ab485 --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d31d3d26654e42668fa2a244cfff96ca88884982865135f758df76307cc0e1f +size 1056785184 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-Q4_1.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-Q4_1.gguf new file mode 100644 index 0000000..4051efd --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dac138421b273fd81e543b77a4b616414ffb0369ea8ab5fffc6879c9f96ec5a +size 1142506272 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-Q4_K_M.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-Q4_K_M.gguf new file mode 100644 index 0000000..b895784 --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41585cb2b12914d817c1e130a14bbe082ccecf1aa2e89836ed317514bb043344 +size 1107411744 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-Q4_K_S.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-Q4_K_S.gguf new file mode 100644 index 0000000..830d558 --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f3c0fb258368d4d22a45209f33918af3a06d95133e9d6ddb16c2ce49394e8d2 +size 1060193056 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-Q5_K_M.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-Q5_K_M.gguf new file mode 100644 index 0000000..5b4784f --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8753cc72288e89930b03da3f7b8397d1d669b754e9e7f6b5ac9efdab9dcb4c3 +size 1257882400 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-Q5_K_S.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-Q5_K_S.gguf new file mode 100644 index 0000000..22af3f6 --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:844f9a8adb28f46157eacd927bf5105fe5a94823328acd28a1ea111824e0767f +size 1230586656 diff --git a/Qwen3-VisionCaption-2B-Thinking.i1-Q6_K.gguf b/Qwen3-VisionCaption-2B-Thinking.i1-Q6_K.gguf new file mode 100644 index 0000000..a566a8e --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2618229ce29167ede2c84981eded6790979da303d84797148bfea132e18f0d44 +size 1417757472 diff --git a/Qwen3-VisionCaption-2B-Thinking.imatrix.gguf b/Qwen3-VisionCaption-2B-Thinking.imatrix.gguf new file mode 100644 index 0000000..56fc9f7 --- /dev/null +++ b/Qwen3-VisionCaption-2B-Thinking.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07c5a5a3587a7172bc9be278c180855eea14a8135f618a379e9b82b8d54dc327 +size 2094560 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1965f07 --- /dev/null +++ b/README.md @@ -0,0 +1,97 @@ +--- +base_model: prithivMLmods/Qwen3-VisionCaption-2B-Thinking +datasets: +- prithivMLmods/blip3o-caption-mini-arrow +- prithivMLmods/Caption3o-Opt-v2 +language: +- en +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- image-caption +- abliterated +- uncensored +- llama.cpp +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/prithivMLmods/Qwen3-VisionCaption-2B-Thinking + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VisionCaption-2B-Thinking-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-GGUF + +**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-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/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-IQ1_S.gguf) | i1-IQ1_S | 0.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-IQ1_M.gguf) | i1-IQ1_M | 0.6 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-IQ2_S.gguf) | i1-IQ2_S | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-IQ2_M.gguf) | i1-IQ2_M | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.8 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-Q2_K.gguf) | i1-Q2_K | 0.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-IQ3_S.gguf) | i1-IQ3_S | 1.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-IQ3_M.gguf) | i1-IQ3_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.1 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.2 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-Q4_0.gguf) | i1-Q4_0 | 1.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-Q4_1.gguf) | i1-Q4_1 | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-Thinking.i1-Q6_K.gguf) | i1-Q6_K | 1.5 | 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. + +