From ea90d7faa46cf541227dbfa9bac231322be4f9f3 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 27 Sep 2026 12:35:18 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF Source: Original Platform --- .gitattributes | 60 ++++++++++++++++++++++++ Qwen3-8B-ERP-v0.1.i1-IQ1_M.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-IQ1_S.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-IQ2_M.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-IQ2_S.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-IQ2_XS.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-IQ2_XXS.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-IQ3_M.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-IQ3_S.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-IQ3_XS.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-IQ3_XXS.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-IQ4_NL.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-IQ4_XS.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-Q2_K.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-Q2_K_S.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-Q3_K_L.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-Q3_K_M.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-Q3_K_S.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-Q4_0.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-Q4_1.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-Q4_K_M.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-Q4_K_S.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-Q5_K_M.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-Q5_K_S.gguf | 3 ++ Qwen3-8B-ERP-v0.1.i1-Q6_K.gguf | 3 ++ README.md | 76 +++++++++++++++++++++++++++++++ imatrix.dat | 3 ++ 27 files changed, 211 insertions(+) create mode 100644 .gitattributes create mode 100644 Qwen3-8B-ERP-v0.1.i1-IQ1_M.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-IQ1_S.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-IQ2_M.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-IQ2_S.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-IQ2_XS.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-IQ2_XXS.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-IQ3_M.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-IQ3_S.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-IQ3_XS.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-IQ3_XXS.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-IQ4_NL.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-IQ4_XS.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-Q2_K.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-Q2_K_S.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-Q3_K_L.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-Q3_K_M.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-Q3_K_S.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-Q4_0.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-Q4_1.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-Q4_K_M.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-Q4_K_S.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-Q5_K_M.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-Q5_K_S.gguf create mode 100644 Qwen3-8B-ERP-v0.1.i1-Q6_K.gguf create mode 100644 README.md create mode 100644 imatrix.dat diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0aa027e --- /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 +Qwen3-8B-ERP-v0.1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-8B-ERP-v0.1.i1-IQ1_M.gguf b/Qwen3-8B-ERP-v0.1.i1-IQ1_M.gguf new file mode 100644 index 0000000..38da124 --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57a7e5620cd75309fb370b30dbf28c8a0eb2416c4518961789f9ca3fb429252a +size 2256148288 diff --git a/Qwen3-8B-ERP-v0.1.i1-IQ1_S.gguf b/Qwen3-8B-ERP-v0.1.i1-IQ1_S.gguf new file mode 100644 index 0000000..7bdb65c --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6f0ba95f995b9c21ad5e05f2244fe3fb6470fa6c033b9bcdd8f4727b0bf275e +size 2115770176 diff --git a/Qwen3-8B-ERP-v0.1.i1-IQ2_M.gguf b/Qwen3-8B-ERP-v0.1.i1-IQ2_M.gguf new file mode 100644 index 0000000..6f45120 --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af6d0ea7e7cd0e911539fe79ad360c3bd81da40f4d0d9612a9a7be07c1bb0448 +size 3051915072 diff --git a/Qwen3-8B-ERP-v0.1.i1-IQ2_S.gguf b/Qwen3-8B-ERP-v0.1.i1-IQ2_S.gguf new file mode 100644 index 0000000..ccec9e7 --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc96d07b1aa7fc1a7922cb2fcf7e7bd45ec73da0a6344b6e777174257443fee0 +size 2864744256 diff --git a/Qwen3-8B-ERP-v0.1.i1-IQ2_XS.gguf b/Qwen3-8B-ERP-v0.1.i1-IQ2_XS.gguf new file mode 100644 index 0000000..d93005d --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de8fad44caff31a3c0dbeb2ee08d13cb8baf4f766f32679b2260b2f49766a1f5 +size 2696156992 diff --git a/Qwen3-8B-ERP-v0.1.i1-IQ2_XXS.gguf b/Qwen3-8B-ERP-v0.1.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..8ab4fcb --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cfd31313ee760c7920cea56e0ef6bdceb2d0ca01b2980e72b5729dcbb7a0a68 +size 2490111808 diff --git a/Qwen3-8B-ERP-v0.1.i1-IQ3_M.gguf b/Qwen3-8B-ERP-v0.1.i1-IQ3_M.gguf new file mode 100644 index 0000000..4607f04 --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc82c615647643f687121f84d0ca4cb7bc4c56f3cb41177423d05c012c2420b7 +size 3896620864 diff --git a/Qwen3-8B-ERP-v0.1.i1-IQ3_S.gguf b/Qwen3-8B-ERP-v0.1.i1-IQ3_S.gguf new file mode 100644 index 0000000..9d405e1 --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89552a9ce2ee6eac01575a43d3370aea372af67aa968c4866c20e921d3e8502c +size 3789666112 diff --git a/Qwen3-8B-ERP-v0.1.i1-IQ3_XS.gguf b/Qwen3-8B-ERP-v0.1.i1-IQ3_XS.gguf new file mode 100644 index 0000000..4a2ee4f --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e58eda39a311789a0cfe75c9ef488e0da2d410c0876bde207453d5a9b46a05c +size 3626874688 diff --git a/Qwen3-8B-ERP-v0.1.i1-IQ3_XXS.gguf b/Qwen3-8B-ERP-v0.1.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..551baa0 --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e39d9ee45d4d9ca8a3d3160498fd7748179cb4607ce50a5fcfa90adaa3cd31a7 +size 3369633600 diff --git a/Qwen3-8B-ERP-v0.1.i1-IQ4_NL.gguf b/Qwen3-8B-ERP-v0.1.i1-IQ4_NL.gguf new file mode 100644 index 0000000..52ecb0c --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adfe60f20ee5f24acbf5fc9d5279395a120a51066d536b662b69d63018ef9c35 +size 4793624384 diff --git a/Qwen3-8B-ERP-v0.1.i1-IQ4_XS.gguf b/Qwen3-8B-ERP-v0.1.i1-IQ4_XS.gguf new file mode 100644 index 0000000..7c35893 --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3afede9e928acf235bcf561e7b19f5b056e991123dae429b4bf08954d952a97 +size 4561839936 diff --git a/Qwen3-8B-ERP-v0.1.i1-Q2_K.gguf b/Qwen3-8B-ERP-v0.1.i1-Q2_K.gguf new file mode 100644 index 0000000..4036324 --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b56ce08a38cda760fc921f986fe12aa48cd9e1752288e1ab3b4193566c01abc +size 3281733440 diff --git a/Qwen3-8B-ERP-v0.1.i1-Q2_K_S.gguf b/Qwen3-8B-ERP-v0.1.i1-Q2_K_S.gguf new file mode 100644 index 0000000..b693b4b --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fa60cc1900551ce80850ba2b6c2dbbea281f46b56351acae77efc818dcc375a +size 3083552576 diff --git a/Qwen3-8B-ERP-v0.1.i1-Q3_K_L.gguf b/Qwen3-8B-ERP-v0.1.i1-Q3_K_L.gguf new file mode 100644 index 0000000..1eeb16e --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b5b91152ff0e2f7dfab7aa37bc7f80fe0dd1767da4f19d35670c6885874e911 +size 4431394624 diff --git a/Qwen3-8B-ERP-v0.1.i1-Q3_K_M.gguf b/Qwen3-8B-ERP-v0.1.i1-Q3_K_M.gguf new file mode 100644 index 0000000..dcd8e5e --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc12049430d6faa16b135711e9ac35ba635e4134821acbcb0412c6f23d162376 +size 4124161856 diff --git a/Qwen3-8B-ERP-v0.1.i1-Q3_K_S.gguf b/Qwen3-8B-ERP-v0.1.i1-Q3_K_S.gguf new file mode 100644 index 0000000..1e95f7c --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97bca31528773a54416a4200c787e58559532f234f37564e4bb5fd51266514b0 +size 3769612096 diff --git a/Qwen3-8B-ERP-v0.1.i1-Q4_0.gguf b/Qwen3-8B-ERP-v0.1.i1-Q4_0.gguf new file mode 100644 index 0000000..e274a9f --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:322442b06424ffd679973f86d56bd04202612ba3faf1df178276dba92a193401 +size 4787332928 diff --git a/Qwen3-8B-ERP-v0.1.i1-Q4_1.gguf b/Qwen3-8B-ERP-v0.1.i1-Q4_1.gguf new file mode 100644 index 0000000..dffcc0b --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43cde281ca801dcc104301ef965377dace6f57c4d49ed005fb8163bfda3ae779 +size 5247756096 diff --git a/Qwen3-8B-ERP-v0.1.i1-Q4_K_M.gguf b/Qwen3-8B-ERP-v0.1.i1-Q4_K_M.gguf new file mode 100644 index 0000000..688420b --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4ba08047f1b94734e1312aa32351efdf99b27728c5b4483b021dcef7574dea4 +size 5027784512 diff --git a/Qwen3-8B-ERP-v0.1.i1-Q4_K_S.gguf b/Qwen3-8B-ERP-v0.1.i1-Q4_K_S.gguf new file mode 100644 index 0000000..c468e5f --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee743602b13e89ea83c0af5c3cb27ddb392dba1bf3d17552ae102d95c58c4856 +size 4802012992 diff --git a/Qwen3-8B-ERP-v0.1.i1-Q5_K_M.gguf b/Qwen3-8B-ERP-v0.1.i1-Q5_K_M.gguf new file mode 100644 index 0000000..05ba32a --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8963a60a6fdaf328293012754255dc5ffb8acbd82d59775cb0163d270196857 +size 5851113280 diff --git a/Qwen3-8B-ERP-v0.1.i1-Q5_K_S.gguf b/Qwen3-8B-ERP-v0.1.i1-Q5_K_S.gguf new file mode 100644 index 0000000..db48d77 --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68a87e5a9f978e228e455b20042319e8afdd784a371c015dcc7fd692d3633163 +size 5720762176 diff --git a/Qwen3-8B-ERP-v0.1.i1-Q6_K.gguf b/Qwen3-8B-ERP-v0.1.i1-Q6_K.gguf new file mode 100644 index 0000000..87fc374 --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7b55de34b5fe8c1807f533cee9fdd4782fb5357fb7d0fd36718e72a649bea25 +size 6725900096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..851114d --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: Aratako/Qwen3-8B-ERP-v0.1 +language: +- ja +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Aratako/Qwen3-8B-ERP-v0.1 + + +static quants are available at https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-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/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-IQ1_S.gguf) | i1-IQ1_S | 2.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-IQ1_M.gguf) | i1-IQ1_M | 2.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-IQ2_S.gguf) | i1-IQ2_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-IQ2_M.gguf) | i1-IQ2_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.2 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-Q2_K.gguf) | i1-Q2_K | 3.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.9 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-IQ3_S.gguf) | i1-IQ3_S | 3.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-IQ3_M.gguf) | i1-IQ3_M | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-Q4_0.gguf) | i1-Q4_0 | 4.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.9 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-Q4_1.gguf) | i1-Q4_1 | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-i1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.i1-Q6_K.gguf) | i1-Q6_K | 6.8 | 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..fa04b2b --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c655662d2b3a9d720c1b2428cb18cf02566a382c593540f3b0f3c3f0e5d5959 +size 5316769