commit bfb201e3a2beae099f2ad5ae5e2159fc1171d35b Author: ModelHub XC Date: Wed Apr 29 18:30:08 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0ff96b9 --- /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-it-REDACTED.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VisionCaption-2B-it-REDACTED.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ1_M.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ1_M.gguf new file mode 100644 index 0000000..c644fa5 --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0ab3792dc71892c5e405633f00bfcd17435c220950e16fce7e2d385e532ca33 +size 543795968 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ1_S.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ1_S.gguf new file mode 100644 index 0000000..024886e --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:787c69561b23db552389135cbcab1c29d5233122be10a877641083432ff0a515 +size 515779328 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ2_M.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ2_M.gguf new file mode 100644 index 0000000..025e680 --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:757a6363775c1a588a6bc760609b5016a00bde335e0726ca60bd77c1baf3a9a4 +size 695184128 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ2_S.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ2_S.gguf new file mode 100644 index 0000000..58446b5 --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ca19e1033f1c55f967bcb75a9b6eac24e0776cceb6188f5c276637bc1598138 +size 657828608 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ2_XS.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ2_XS.gguf new file mode 100644 index 0000000..fd73064 --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecc190ccee53822b925c1222b168e6df73926b5e2ac6700d21e505d68be4c641 +size 631515904 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ2_XXS.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..7f641e5 --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b483b68ba79bda8ca0c71e17c03104a772e379156bf68ba43fe807adc343052 +size 590490368 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ3_M.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ3_M.gguf new file mode 100644 index 0000000..337e410 --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47cbd73d2aff7f787b6a6d99a3b9d9d0d8bfac591629473029e835d3932e93c0 +size 895664896 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ3_S.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ3_S.gguf new file mode 100644 index 0000000..ee65de1 --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8fab282ee82c689f4a4505e4044e1b4fc17d05c64e7dc13ffcac808c390007f +size 867255040 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ3_XS.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ3_XS.gguf new file mode 100644 index 0000000..3930fe2 --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:781122c6b7a7057d50889f4aa0435ffc717dbd11e4511bc0f2550c088d933c57 +size 834224896 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ3_XXS.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..219ea56 --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d53ff33d103d016f754c6efe1b9a3e8578b4d06b5bf923b23da145256eeccc9 +size 754363136 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ4_NL.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ4_NL.gguf new file mode 100644 index 0000000..f066e7a --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6439ed3c9327e5e0ca33650138c9703c41074fd4340f6ca99db0b07e9e4453ac +size 1054425856 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ4_XS.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ4_XS.gguf new file mode 100644 index 0000000..fb324b0 --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bce2a713dc8c78c5861e9f567113602dde5fc1e86179edf2adb50ce429627bf +size 1010385664 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q2_K.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q2_K.gguf new file mode 100644 index 0000000..4334b23 --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81e911209b7facda55054b20bdc0d8da56ec13dc53bed66ce50137324ae07dce +size 777798400 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q2_K_S.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q2_K_S.gguf new file mode 100644 index 0000000..de25c66 --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae830ad754d0b5f83bef1dca67be007b16bb3f53f5081ff2a03ee5bb9ac3cf61 +size 732971776 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q3_K_L.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q3_K_L.gguf new file mode 100644 index 0000000..2e89d22 --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9f75e566cd9a1487b6cac468b0e5d440227c48cefed63155b7306c9ef19c9d6 +size 1003504384 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q3_K_M.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q3_K_M.gguf new file mode 100644 index 0000000..19abc3f --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34c0cb9d1c441d8f6e99844c0fb88d210dc73d7769ce4a004eeabb437e4b9efa +size 939541248 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q3_K_S.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q3_K_S.gguf new file mode 100644 index 0000000..1cee2ad --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ea7e0e4ec7acf413d57d837ed3a9cb494aa6e2b21fb209b6869a4cc0d917402 +size 867255040 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q4_0.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q4_0.gguf new file mode 100644 index 0000000..d3fb252 --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03e02edf109f7d97b3ff1e681f26a417dc532fb1623c1c55cc6f2fa9789d38e6 +size 1056785152 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q4_1.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q4_1.gguf new file mode 100644 index 0000000..65596c7 --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65272f7a36e402f8f5e21ae8d92cc27386c04a4e2bac75c668368e30258e6666 +size 1142506240 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q4_K_M.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q4_K_M.gguf new file mode 100644 index 0000000..d857637 --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04a24716469001cffaa503614299314e2bca2ad0d00a686988dac45b2eaf5a80 +size 1107411712 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q4_K_S.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q4_K_S.gguf new file mode 100644 index 0000000..59c6dac --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bac2074dca8c7cadaf02f63c96c0812f096d8c3381e1f9b094dbbeb50998e49c +size 1060193024 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q5_K_M.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q5_K_M.gguf new file mode 100644 index 0000000..5434c2a --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0717b0edcbf8510f57c9c97938cf8ce59dfcda129964f16b2b1f512c466243b +size 1257882368 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q5_K_S.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q5_K_S.gguf new file mode 100644 index 0000000..fc4466a --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73eb4e27fab10bb131d86de4cffe553bb2e8c1c8ebb7a8ae22bfc0c7ae0371ba +size 1230586624 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q6_K.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q6_K.gguf new file mode 100644 index 0000000..3438421 --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02e72d7312ed5c91b83a568358cc1ec1f3019a82dc76332d20212b9103381acf +size 1417757440 diff --git a/Qwen3-VisionCaption-2B-it-REDACTED.imatrix.gguf b/Qwen3-VisionCaption-2B-it-REDACTED.imatrix.gguf new file mode 100644 index 0000000..9a1ae74 --- /dev/null +++ b/Qwen3-VisionCaption-2B-it-REDACTED.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b039e81de8cdb5eca7bcd6120740bca60ff6f35127758e261118d4968e534777 +size 2094560 diff --git a/README.md b/README.md new file mode 100644 index 0000000..57c4f87 --- /dev/null +++ b/README.md @@ -0,0 +1,96 @@ +--- +base_model: prithivMLmods/Qwen3-VisionCaption-2B-it-REDACTED +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 +- censored +- llama.cpp +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/prithivMLmods/Qwen3-VisionCaption-2B-it-REDACTED + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-GGUF + +**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-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-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ1_S.gguf) | i1-IQ1_S | 0.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ1_M.gguf) | i1-IQ1_M | 0.6 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ2_S.gguf) | i1-IQ2_S | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ2_M.gguf) | i1-IQ2_M | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.8 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q2_K.gguf) | i1-Q2_K | 0.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ3_S.gguf) | i1-IQ3_S | 1.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ3_M.gguf) | i1-IQ3_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.1 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.2 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q4_0.gguf) | i1-Q4_0 | 1.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q4_1.gguf) | i1-Q4_1 | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VisionCaption-2B-it-REDACTED-i1-GGUF/resolve/main/Qwen3-VisionCaption-2B-it-REDACTED.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. + +