commit 16e7d093359ce550268543efde80b343f60942e4 Author: ModelHub XC Date: Thu May 28 13:02:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-VisionCaption-2B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d9bb1ff --- /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.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VisionCaption-2B.i1-IQ1_M.gguf b/Qwen3-VisionCaption-2B.i1-IQ1_M.gguf new file mode 100644 index 0000000..63ecd57 --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:408446ad601a7f62dff459ead0b8f8a2f261af474219ea3182542809613739cc +size 543796000 diff --git a/Qwen3-VisionCaption-2B.i1-IQ1_S.gguf b/Qwen3-VisionCaption-2B.i1-IQ1_S.gguf new file mode 100644 index 0000000..7a5284b --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59d2c54e07fa774f0c2ad07c468d81baeff17c11f6641814cfb0a3d16bd600ec +size 515779360 diff --git a/Qwen3-VisionCaption-2B.i1-IQ2_M.gguf b/Qwen3-VisionCaption-2B.i1-IQ2_M.gguf new file mode 100644 index 0000000..fe99164 --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f5ae8471c4f6c3f4d52091140132aa2218909c514799a19ddff1faca5f2af89 +size 695184160 diff --git a/Qwen3-VisionCaption-2B.i1-IQ2_S.gguf b/Qwen3-VisionCaption-2B.i1-IQ2_S.gguf new file mode 100644 index 0000000..06ec081 --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55caca362078af906c5cc4ac0eb54cf86f49616923929b9977b930f91f77a1b6 +size 657828640 diff --git a/Qwen3-VisionCaption-2B.i1-IQ2_XS.gguf b/Qwen3-VisionCaption-2B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..3fdc427 --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1899abb39044621f41e3419dddb038abae2a9e871f958eb7b21b85f1f7a749dc +size 631515936 diff --git a/Qwen3-VisionCaption-2B.i1-IQ2_XXS.gguf b/Qwen3-VisionCaption-2B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..9dc9163 --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc01cff7d7e47dd3b5577aa8e97a6dff17166a33cf08521b7c7a871ef67f619f +size 590490400 diff --git a/Qwen3-VisionCaption-2B.i1-IQ3_M.gguf b/Qwen3-VisionCaption-2B.i1-IQ3_M.gguf new file mode 100644 index 0000000..7a8ed12 --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99aca157f7cbda6a9c5aea95c728a9632d0d29a7a2fca7bd37bc7a9f4301cab8 +size 895664928 diff --git a/Qwen3-VisionCaption-2B.i1-IQ3_S.gguf b/Qwen3-VisionCaption-2B.i1-IQ3_S.gguf new file mode 100644 index 0000000..ab487f1 --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c1e12bd24c595769a7661ff4a034c2c9ba9014c79b8d0fdfa78456c50721c4f +size 867255072 diff --git a/Qwen3-VisionCaption-2B.i1-IQ3_XS.gguf b/Qwen3-VisionCaption-2B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..29cb817 --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd3287aff037267f90152051f4383f3642759acc036be8a780f945d0c4cef00a +size 834224928 diff --git a/Qwen3-VisionCaption-2B.i1-IQ3_XXS.gguf b/Qwen3-VisionCaption-2B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..fc12362 --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01ed65fa5ab4023a8a1bf65a3a08b5ef4653dd40e510c62bef6cf5e9f0102c59 +size 754363168 diff --git a/Qwen3-VisionCaption-2B.i1-IQ4_NL.gguf b/Qwen3-VisionCaption-2B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..0698346 --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08edb579dd0a97cc80ef04f9490d7f0834d3035de733b065725fe2c09d449219 +size 1054425888 diff --git a/Qwen3-VisionCaption-2B.i1-IQ4_XS.gguf b/Qwen3-VisionCaption-2B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..8561079 --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5dba17844ce1af65fd377e53f8cb9d4b4418210780ac1ed9d3f0f804171ebdb +size 1010385696 diff --git a/Qwen3-VisionCaption-2B.i1-Q2_K.gguf b/Qwen3-VisionCaption-2B.i1-Q2_K.gguf new file mode 100644 index 0000000..8dda6c3 --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98e6839c8f53637156aa28e211c3545e23bc37035b9007fbc80c13f1a389b8f9 +size 777798432 diff --git a/Qwen3-VisionCaption-2B.i1-Q2_K_S.gguf b/Qwen3-VisionCaption-2B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..ba8f94a --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58058baf92d0550de7478a108daaac0855d9a89aa242125252fa44e94bd8ef42 +size 732971808 diff --git a/Qwen3-VisionCaption-2B.i1-Q3_K_L.gguf b/Qwen3-VisionCaption-2B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..31bc211 --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fbf7b3eae23075a7b42413bf5fdb56db680f595f5391057954efd9be47de9ff +size 1003504416 diff --git a/Qwen3-VisionCaption-2B.i1-Q3_K_M.gguf b/Qwen3-VisionCaption-2B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..3c2e988 --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8389e94518deb8f099c1cebb4df09add0afbfdbf9a032135ddaef65f463021b4 +size 939541280 diff --git a/Qwen3-VisionCaption-2B.i1-Q3_K_S.gguf b/Qwen3-VisionCaption-2B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..5cfee56 --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bca6619a38982db1e9b55bbef0421521526cf2db1b522fd5e810975b0478f2c2 +size 867255072 diff --git a/Qwen3-VisionCaption-2B.i1-Q4_0.gguf b/Qwen3-VisionCaption-2B.i1-Q4_0.gguf new file mode 100644 index 0000000..6c0c188 --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b3da6c1e4312f2a219e7c554c7182d9698bd8fcc2581ce6f216ff7e9a772350 +size 1056785184 diff --git a/Qwen3-VisionCaption-2B.i1-Q4_1.gguf b/Qwen3-VisionCaption-2B.i1-Q4_1.gguf new file mode 100644 index 0000000..5d528cb --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bf0035d017a2aa12968e395ff4442ee9a24f8b82b79f8ecc723a610c4cd9366 +size 1142506272 diff --git a/Qwen3-VisionCaption-2B.i1-Q4_K_M.gguf b/Qwen3-VisionCaption-2B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..6cc8401 --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42554506672fbed8a0aeb411b0124fddfcfa41e7f6412403dce55143fa1d62a6 +size 1107411744 diff --git a/Qwen3-VisionCaption-2B.i1-Q4_K_S.gguf b/Qwen3-VisionCaption-2B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..84b3b2a --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18149d8d2dcf15e10abf2a272dcc92d802e00554fe34bd4db21585af17cd385c +size 1060193056 diff --git a/Qwen3-VisionCaption-2B.i1-Q5_K_M.gguf b/Qwen3-VisionCaption-2B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..21bbd41 --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2503899ffa441037b47033afde80955fff1a9fb579636294728107258ed3bf19 +size 1257882400 diff --git a/Qwen3-VisionCaption-2B.i1-Q5_K_S.gguf b/Qwen3-VisionCaption-2B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..79b0237 --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdd9b90135b9f78b12dacc7553e6d9efb57d6c8ecb9e8ded560524df55ace50e +size 1230586656 diff --git a/Qwen3-VisionCaption-2B.i1-Q6_K.gguf b/Qwen3-VisionCaption-2B.i1-Q6_K.gguf new file mode 100644 index 0000000..3282863 --- /dev/null +++ b/Qwen3-VisionCaption-2B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f22be6486f94b0f709f068762223c3ae460f306d769b5503e571bc62fb8124f1 +size 1417757472 diff --git a/Qwen3-VisionCaption-2B.imatrix.gguf b/Qwen3-VisionCaption-2B.imatrix.gguf new file mode 100644 index 0000000..ba713b8 --- /dev/null +++ b/Qwen3-VisionCaption-2B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76c8f0d58a256d3dfdbb03596800c765703398c9b0b7236e74fcec8e6e858da1 +size 2094560 diff --git a/README.md b/README.md new file mode 100644 index 0000000..33e6242 --- /dev/null +++ b/README.md @@ -0,0 +1,97 @@ +--- +base_model: prithivMLmods/Qwen3-VisionCaption-2B +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 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VisionCaption-2B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-GGUF + +**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-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-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-IQ1_S.gguf) | i1-IQ1_S | 0.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-IQ1_M.gguf) | i1-IQ1_M | 0.6 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-IQ2_S.gguf) | i1-IQ2_S | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-IQ2_M.gguf) | i1-IQ2_M | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.8 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-Q2_K.gguf) | i1-Q2_K | 0.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-IQ3_S.gguf) | i1-IQ3_S | 1.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-IQ3_M.gguf) | i1-IQ3_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.1 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.2 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-Q4_0.gguf) | i1-Q4_0 | 1.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-Q4_1.gguf) | i1-Q4_1 | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B.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. + +