commit 17fb083ef53266504c88643a89b96307c8d4e169 Author: ModelHub XC Date: Mon May 18 16:04:06 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2fbea1d --- /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 +KAIROS-MM-Qwen2.5-VL-7B-SFT.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ1_M.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ1_M.gguf new file mode 100644 index 0000000..d79075e --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f18688d82ad451b447cc8983299e7857b13a2cc574ff4c7b3fad80dccc9e1a34 +size 2042196384 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ1_S.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ1_S.gguf new file mode 100644 index 0000000..c81abee --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12b95978e8ab38ba666f672e1a4bbb88021960b2f209ff1074a014ce8dbdae6a +size 1903667616 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ2_M.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ2_M.gguf new file mode 100644 index 0000000..c64d9ce --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4888f2e58132f968df65061abb6e96a52c67812c21f2fac13ec41e194bd3e0d +size 2780342688 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ2_S.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ2_S.gguf new file mode 100644 index 0000000..5c2f0f0 --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d1f3c1ce33373a6f77b5e31a07cec8570763f5f17847f651b839dc1f8d0e6dc +size 2595637664 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ2_XS.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ2_XS.gguf new file mode 100644 index 0000000..1819621 --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b04f549f6f1b87dbff2508912fa07d7538b2349a6e78598ff2c67fac93c8ccee +size 2469022112 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ2_XXS.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..d804305 --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dca382202a58dea12765d3789beb8b9b5ff70a971fa3cebed135ed9717d51b4 +size 2273077664 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ3_M.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ3_M.gguf new file mode 100644 index 0000000..09a6938 --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f27bbf06e4879b4649fcb2eb6f6ec8a4d872619b28f9160a6064e154950fccd +size 3574012320 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ3_S.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ3_S.gguf new file mode 100644 index 0000000..8f2aa77 --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e633d470a913d41d096da1d51bfb05f69f357fe049dd91f5225a84ae28bd9991 +size 3499192736 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ3_XS.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ3_XS.gguf new file mode 100644 index 0000000..0497b94 --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee2ee27f28f88f0b916b58e0c424322e255433516d3a474d8a933ba46ad30a0c +size 3346256288 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ3_XXS.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..ecf311e --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c2a95c7f5c64ccfaac8e86f1921851afc36f062ceb4704d9e272d6ca2ec0ca3 +size 3114514848 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ4_NL.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ4_NL.gguf new file mode 100644 index 0000000..860951c --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8163e81ee0a638e9e5ade49f0db8ac1096d88e21b2e6c88a1692c57d37f58f33 +size 4437813664 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ4_XS.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ4_XS.gguf new file mode 100644 index 0000000..03a5c31 --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bbb54b78e451fa9c755fe2f8b8b838bb253193535654545e915672ac79b7f0d +size 4218472864 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q2_K.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q2_K.gguf new file mode 100644 index 0000000..ed246fb --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3a982383df7f860cb5b72c3d6f7ebd9be7effd7236da882eb752c257307fc12 +size 3015940512 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q2_K_S.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q2_K_S.gguf new file mode 100644 index 0000000..0f40a2c --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c57d2ef3dede359a88e4e4a6454a7933a2130e5c742925dd71142460475fd8f +size 2834074016 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q3_K_L.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q3_K_L.gguf new file mode 100644 index 0000000..4f4e9a5 --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49156bd6cf96d5375f68b57033a84fd9b3f4fd2c2542472f851e3d2fb092b98f +size 4088459680 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q3_K_M.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q3_K_M.gguf new file mode 100644 index 0000000..ca9e811 --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28fd3d1d0e0c913cd166ba709721e712b3cbd7baa0ba9e102ea4626f2897d6ad +size 3808391584 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q3_K_S.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q3_K_S.gguf new file mode 100644 index 0000000..baa49bb --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7597223b5c4539b53149aebde61885e4c89e682ba5334fba5f8c1060d770433b +size 3492368800 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q4_0.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q4_0.gguf new file mode 100644 index 0000000..f0534b3 --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9efe294a545773d6e6c28fa14ce506e6f32af99005e8003207f12f97fed3f047 +size 4444121504 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q4_1.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q4_1.gguf new file mode 100644 index 0000000..555d60d --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50fb203e5a740a13d1452bca9e3711707bbc989354d973c5c0da4a8b4f4002b0 +size 4873284000 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q4_K_M.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q4_K_M.gguf new file mode 100644 index 0000000..97c0a24 --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87250c154e1912130b36d7edf6b67009b0f1c9085cd6e42925ccab5f3301b4ef +size 4683073952 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q4_K_S.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q4_K_S.gguf new file mode 100644 index 0000000..8788571 --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1a4c60dcb87dccf2f4e8a4dfc84e7a2234c25f5aa7d03ca280b2d7e54febc5c +size 4457769376 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q5_K_M.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q5_K_M.gguf new file mode 100644 index 0000000..bda716f --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e79be0cb86854f9c4a09b0bd4b6524fee9dd1480cba14bfb5686497bc8e33d7 +size 5444831648 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q5_K_S.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q5_K_S.gguf new file mode 100644 index 0000000..ab1671f --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d394650e8ddc40255a12b3c4054044b1b25fb17660921f04ab6bd88e21a9a7c +size 5315176864 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q6_K.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q6_K.gguf new file mode 100644 index 0000000..a52f0ad --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3f52e4796957ed48dae4a47598473b977d867a46ccf8d7e659800f739252db9 +size 6254199200 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.imatrix.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.imatrix.gguf new file mode 100644 index 0000000..2f24c5f --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcbbe5349641bf33f03693807420a6fed6df0640f09471e7fce39aa42c8a7dc8 +size 4560352 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b32aed6 --- /dev/null +++ b/README.md @@ -0,0 +1,102 @@ +--- +base_model: prithivMLmods/KAIROS-MM-Qwen2.5-VL-7B-SFT +datasets: +- allenai/SAGE-MM-SFT-417K +- nvidia/Cosmos-Reason1-SFT-Dataset +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- trl +- video-reasoning +- text-generation-inference +- pytorch +- agent +- reasoning +- long-horizon-reasoning +- temporal-reasoning +- spatial-reasoning +- physical-reasoning +- common-sense-reasoning +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/prithivMLmods/KAIROS-MM-Qwen2.5-VL-7B-SFT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-GGUF + +**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-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/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.9 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q4_1.gguf) | i1-Q4_1 | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-i1-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | 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. + +