commit 6e746f17da88cc8e913d881252596c0778854f41 Author: ModelHub XC Date: Fri Jul 10 08:54:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4081808 --- /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 +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-bf16.gguf filter=lfs diff=lfs merge=lfs -text +Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1.imatrix filter=lfs diff=lfs merge=lfs -text diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ2_M.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ2_M.gguf new file mode 100644 index 0000000..bd081e7 --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bf2e7148b8e84348464c792c376f28eb0afda7d09c05442b4d9629513c4c789 +size 3051914720 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ3_M.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ3_M.gguf new file mode 100644 index 0000000..eb80d94 --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f5a110e38dd287c1626f5e9f786d9c709357cd056b7a5fa7a2adae12ab9716a +size 3896620512 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ3_XS.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ3_XS.gguf new file mode 100644 index 0000000..eebc968 --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a5921c3a8724cf7e278ad95630e2ea2651177f7c120356f6c9d98b41efe16ae +size 3626874336 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ3_XXS.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ3_XXS.gguf new file mode 100644 index 0000000..751920b --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0388f24629f4d14bc04b814c52da1060c67bb19e979ac4579babcf1d1a1d28c3 +size 3369633248 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ4_NL.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ4_NL.gguf new file mode 100644 index 0000000..beb2643 --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df7cf755a5db249c9dc068d9fafa9e0c9639c3069a94e676ea6187b4b284bd47 +size 4793624032 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ4_XS.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ4_XS.gguf new file mode 100644 index 0000000..ed968e9 --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c20e614714b7c3a5a8f8685be58d4c256e472903a98f5d769647c896e77eca4 +size 4561839584 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q2_K.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q2_K.gguf new file mode 100644 index 0000000..dc9b5f5 --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eb3af7bb40c3142381e2e6a0be08dfbe314ad074c376c9c76ca992a2118d171 +size 3281733088 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q2_K_L.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q2_K_L.gguf new file mode 100644 index 0000000..e8c6bba --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2080c3c8b4f1d3b86f1e00faeb6d9801d1659a54b1facb37ba48286b325d4fa2 +size 3889477088 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_L.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_L.gguf new file mode 100644 index 0000000..24e6063 --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c1db649cbaae9588640df2793962c238174e232695b8831dd8562bbd32ed986 +size 4431394272 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_M.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_M.gguf new file mode 100644 index 0000000..13af855 --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca5a75042159e1a9ea25be89140c63e83ea200a4fd5184dd95697752a9a36396 +size 4124161504 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_S.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_S.gguf new file mode 100644 index 0000000..8a4cc1d --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae6ed76418819a01abaccbce2b2948506129992eedaa19eb0a6bcaca68aae684 +size 3769611744 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_XL.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_XL.gguf new file mode 100644 index 0000000..cc597d4 --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97555fd43fefdd57c7108a7fa16778119a9634f32ebe2b5b4d8d1f826c99925d +size 4975932896 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_0.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_0.gguf new file mode 100644 index 0000000..9bcf811 --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a6d73291d60c805ed72097c60c76986a87bd21d36decc3f0459a3b190eadf65 +size 4787332576 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_1.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_1.gguf new file mode 100644 index 0000000..74ae76d --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7e50a89de890b8cac53d77a1f44eea90e2184cfb5f2baca806b0c90a1c4e918 +size 5247755744 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_K_L.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_K_L.gguf new file mode 100644 index 0000000..ac01599 --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e54eb435113fdf77c49b1c6c6dea8c54505c702efa293d7f8db78333547f8cd +size 5489669600 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_K_M.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_K_M.gguf new file mode 100644 index 0000000..3724d97 --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bfa61f0f94aa06a58b7e631fe6a51bedef6395135569d049b3c3f96867427be +size 5027784160 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_K_S.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_K_S.gguf new file mode 100644 index 0000000..3a5017c --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fc937ac90e727ccda663be086f8389a286be64617052ca3284521d4ee702b3c +size 4802012640 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q5_K_L.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q5_K_L.gguf new file mode 100644 index 0000000..585fb11 --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80b8ad0a523e0357fd31f0c6d51a58ec1e198d0e20a8777c6b42420184c9eca7 +size 6235207136 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q5_K_M.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q5_K_M.gguf new file mode 100644 index 0000000..f7da661 --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:314f8fa0eae278365cfad3ff4f471e3d45669453c77d3d2297885c2ff2219b7c +size 5851112928 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q5_K_S.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q5_K_S.gguf new file mode 100644 index 0000000..26c324f --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f059670395093baefe7b0c3f0a163162b5b21f0736059ab56303b514b95be4b +size 5720761824 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q6_K.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q6_K.gguf new file mode 100644 index 0000000..587c666 --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a933d09201884b893233ad1680d85a2125b3425d95aca61fc8c914cade3ade4 +size 6725899744 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q6_K_L.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q6_K_L.gguf new file mode 100644 index 0000000..4f82542 --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1623d12a30e1ea1bc7a8fdc535414635d9ee1ddadcd64169df2064627746aae9 +size 7027340768 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q8_0.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q8_0.gguf new file mode 100644 index 0000000..3f86bb7 --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72972cf6c3ee8d7ae7ff1b01c8e81f40ae2bd413949f9976e7c59cce0163714b +size 8709518816 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-bf16.gguf b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-bf16.gguf new file mode 100644 index 0000000..402a07c --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:072f8e44dfa4c37e377eed9e1be7d3da27ad3c56a67a59d89cb2babe50daa0c8 +size 16388043936 diff --git a/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1.imatrix b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1.imatrix new file mode 100644 index 0000000..ae88ee5 --- /dev/null +++ b/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17adc815c808a497a8312679b88142da6985804928c56d49bba577478ccebb3f +size 5316782 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f33a941 --- /dev/null +++ b/README.md @@ -0,0 +1,172 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model: Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1 +tags: +- chat +base_model_relation: quantized +--- + +## Llamacpp imatrix Quantizations of Josiefied-Qwen3-8B-abliterated-v1 by Goekdeniz-Guelmez + +Using llama.cpp release b5270 for quantization. + +Original model: https://huggingface.co/Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1 + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) + +Run them in [LM Studio](https://lmstudio.ai/) + +Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project + +## Prompt format + +``` +<|im_start|>system +{system_prompt}<|im_end|> +<|im_start|>user +{prompt}<|im_end|> +<|im_start|>assistant +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Josiefied-Qwen3-8B-abliterated-v1-bf16.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-bf16.gguf) | bf16 | 16.39GB | false | Full BF16 weights. | +| [Josiefied-Qwen3-8B-abliterated-v1-Q8_0.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q8_0.gguf) | Q8_0 | 8.71GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Josiefied-Qwen3-8B-abliterated-v1-Q6_K_L.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q6_K_L.gguf) | Q6_K_L | 7.03GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Josiefied-Qwen3-8B-abliterated-v1-Q6_K.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q6_K.gguf) | Q6_K | 6.73GB | false | Very high quality, near perfect, *recommended*. | +| [Josiefied-Qwen3-8B-abliterated-v1-Q5_K_L.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q5_K_L.gguf) | Q5_K_L | 6.24GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Josiefied-Qwen3-8B-abliterated-v1-Q5_K_M.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q5_K_M.gguf) | Q5_K_M | 5.85GB | false | High quality, *recommended*. | +| [Josiefied-Qwen3-8B-abliterated-v1-Q5_K_S.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q5_K_S.gguf) | Q5_K_S | 5.72GB | false | High quality, *recommended*. | +| [Josiefied-Qwen3-8B-abliterated-v1-Q4_K_L.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_K_L.gguf) | Q4_K_L | 5.49GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Josiefied-Qwen3-8B-abliterated-v1-Q4_1.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_1.gguf) | Q4_1 | 5.25GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Josiefied-Qwen3-8B-abliterated-v1-Q4_K_M.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_K_M.gguf) | Q4_K_M | 5.03GB | false | Good quality, default size for most use cases, *recommended*. | +| [Josiefied-Qwen3-8B-abliterated-v1-Q3_K_XL.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_XL.gguf) | Q3_K_XL | 4.98GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Josiefied-Qwen3-8B-abliterated-v1-Q4_K_S.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_K_S.gguf) | Q4_K_S | 4.80GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Josiefied-Qwen3-8B-abliterated-v1-Q4_0.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_0.gguf) | Q4_0 | 4.79GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Josiefied-Qwen3-8B-abliterated-v1-IQ4_NL.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ4_NL.gguf) | IQ4_NL | 4.79GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Josiefied-Qwen3-8B-abliterated-v1-IQ4_XS.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ4_XS.gguf) | IQ4_XS | 4.56GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Josiefied-Qwen3-8B-abliterated-v1-Q3_K_L.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_L.gguf) | Q3_K_L | 4.43GB | false | Lower quality but usable, good for low RAM availability. | +| [Josiefied-Qwen3-8B-abliterated-v1-Q3_K_M.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_M.gguf) | Q3_K_M | 4.12GB | false | Low quality. | +| [Josiefied-Qwen3-8B-abliterated-v1-IQ3_M.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ3_M.gguf) | IQ3_M | 3.90GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Josiefied-Qwen3-8B-abliterated-v1-Q2_K_L.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q2_K_L.gguf) | Q2_K_L | 3.89GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Josiefied-Qwen3-8B-abliterated-v1-Q3_K_S.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_S.gguf) | Q3_K_S | 3.77GB | false | Low quality, not recommended. | +| [Josiefied-Qwen3-8B-abliterated-v1-IQ3_XS.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ3_XS.gguf) | IQ3_XS | 3.63GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Josiefied-Qwen3-8B-abliterated-v1-IQ3_XXS.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ3_XXS.gguf) | IQ3_XXS | 3.37GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Josiefied-Qwen3-8B-abliterated-v1-Q2_K.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q2_K.gguf) | Q2_K | 3.28GB | false | Very low quality but surprisingly usable. | +| [Josiefied-Qwen3-8B-abliterated-v1-IQ2_M.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ2_M.gguf) | IQ2_M | 3.05GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | + +## Embed/output weights + +Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. + +## Downloading using huggingface-cli + +
+ Click to view download instructions + +First, make sure you have hugginface-cli installed: + +``` +pip install -U "huggingface_hub[cli]" +``` + +Then, you can target the specific file you want: + +``` +huggingface-cli download bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF --include "Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_K_M.gguf" --local-dir ./ +``` + +If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: + +``` +huggingface-cli download bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF --include "Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q8_0) or download them all in place (./) + +
+ +## ARM/AVX information + +Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass. + +Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly. + +As of llama.cpp build [b4282](https://github.com/ggerganov/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0. + +Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggerganov/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase. + +
+ Click to view Q4_0_X_X information (deprecated + +I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking. + +
+ Click to view benchmarks on an AVX2 system (EPYC7702) + +| model | size | params | backend | threads | test | t/s | % (vs Q4_0) | +| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% | + +Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation + +
+ +
+ +## Which file should I choose? + +
+ Click here for details + +A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) + +The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. + +If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. + +If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. + +Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. + +If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. + +If you want to get more into the weeds, you can check out this extremely useful feature chart: + +[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix) + +But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. + +These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. + +
+ +## Credits + +Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset. + +Thank you ZeroWw for the inspiration to experiment with embed/output. + +Thank you to LM Studio for sponsoring my work. + +Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski