commit 5a6c53e3583677f995a7926b6fcbfb7d79fb5421 Author: ModelHub XC Date: Sat May 9 04:49:51 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b9f5f60 --- /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 +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ1_M.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..2e4d1fd --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54337c386000d5f8394bc80a0f5ee9ade16dbc9cf837a20874d3f9fa1a866595 +size 2042196672 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ1_S.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..fc797f6 --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84e6414ffb3eb343f6eb29ac69aa215057f521b07c96b243d68959caa1afede5 +size 1903667904 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ2_M.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..87fe577 --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c772c8dffc3186b0b2e3a0efb65440d5806b0b4cd36a80545435cc1990ad2b8 +size 2780342976 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ2_S.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..ee1a2de --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a1406d3bd0b62e95840617d56fa7bcc39095700a4e3b452efa92e7bc87277fb +size 2595637952 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ2_XS.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..6b33416 --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74d83ba071005ab674b0f3c4c566acba4fbf6911cdafa9205e96c93647110cbe +size 2469022400 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ2_XXS.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..0c0929a --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10b82ac2a5c5c5e4a1061f835f55303caa3e15b0ae5b990293c35b717a46da67 +size 2273077952 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ3_M.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..8e2577e --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:354dbf9171dac1f6c3a8d6e5137bb40af3030f852fddf04fbbe1d80ae40b82f3 +size 3574012608 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ3_S.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..95804b9 --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d30f21b1cb149362e2e934447f4c9c00b44ac73cc5afa37b0c4a257d5fbe4413 +size 3499193024 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ3_XS.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..f98e8ce --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61ebae7e16f6c8e36e57b6566c2d7616f3119c17a348e1a7849fa0daa71d6d3f +size 3346256576 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ3_XXS.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..d677013 --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc1a5b6b10f9d2e48f3ee8979658706043683f989bcd5097ae07c39bf79d5462 +size 3114515136 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ4_NL.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ4_NL.gguf new file mode 100644 index 0000000..601737b --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f3be8060de29251e125c225a80cdb9d65db0970082c665826ea7d6384d71919 +size 4437813952 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ4_XS.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..fa01763 --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5393d5f5e08ebf9b5c75c9b7a21de00d1121c8c3754b45d689ab4326eea05e50 +size 4218473152 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q2_K.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..d2bbd93 --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3256930654c4c3cdec1232e3afe46ea59774debbb2a99c392d50badd6287281 +size 3015940800 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q2_K_S.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..d5cbb00 --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e665ed7462ec80caa0c9e4485142aedf498539211a4e2fdcce64789f0c823abb +size 2834074304 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q3_K_L.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..56a583e --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9ef62324b84af67f7198620018d5da2a6a3200a72793d0c3ad315c54331976a +size 4088459968 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q3_K_M.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..0d3a99f --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2adfcd41116b30dc4e5125a8b2b7f9ef1852a06af2d99f09dbd606874c9d70fe +size 3808391872 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q3_K_S.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..e9ff60b --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5756519e59fc8eb194e2cccd56ed0340fff51cb2c175b3711b3278a3c67ce7b1 +size 3492369088 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q4_0.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..56425b6 --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e076dbc26fa2912a0496b4d9899c8361122b57f3970f2be2c85d45af02876b3 +size 4444121792 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q4_1.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q4_1.gguf new file mode 100644 index 0000000..95679ff --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66821c4520528ddfddac8abfb5ac94bc56b95907e553b91fe1acc944899cd3d8 +size 4873284288 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q4_K_M.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..a849e87 --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0226fe02298e49f178ca43e376e5ee75ffb37aaa4145a9a0687c05d4aa27d1c6 +size 4683074240 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q4_K_S.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..e50d903 --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69707eda265589197e8b389fb0fd648b266b7a30f4b6648bc51ef5ed5a47a7df +size 4457769664 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q5_K_M.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..c072491 --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aff28896c64ba9f2f408a0d9c4c78c18d482d45f83e2d1855156bce0494da41 +size 5444831936 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q5_K_S.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..b726770 --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:669b484b83a060db9fa203cb622675f1a96197db95e0d4228d42064ef7530aa8 +size 5315177152 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q6_K.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..0265ce1 --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae103ff8c77190c31efcf1a13a94964790df572a3ded0dd32afb4b24866185d4 +size 6254199488 diff --git a/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.imatrix.gguf b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.imatrix.gguf new file mode 100644 index 0000000..e1c56bf --- /dev/null +++ b/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e4619144abd9c0527b87e6b12831e2b126d1dfac5a0c9c54ea7076b706b8498 +size 4560352 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6e793e7 --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: ytz20/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/ytz20/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-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/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.9 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q4_1.gguf) | i1-Q4_1 | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct.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. + +