commit 7022030dfc5d1f1ded32a5a554bfd7cc4e280f46 Author: ModelHub XC Date: Sun May 10 01:15:01 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4b6a035 --- /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-Llama-3.2-3B-Instruct.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ1_M.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..ba9ae08 --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46145f03e6d21bdd578b35f63825a98bc48c2d0703d177b1f274db28b4b15def +size 1053473824 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ1_S.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..afd2924 --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3777bd9ba080a0e9df8f9901266381bd8ece921b0f189b6cf1ecac05b41574b4 +size 997440544 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ2_M.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..6d7a093 --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab6a0528e888297fc8bf505015f117e5d1fc17fedba5a705ac58db91b6043e69 +size 1398330400 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ2_S.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..5b9a160 --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4c01dc718b4400cfb7d81d70ad7c98256ec1d5940bdb059cd7760814207e65c +size 1323619360 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ2_XS.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..55f4312 --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:233ca924d2b00cd9a0d63f787b4f2bbad75f4733f4b1a4fc82b36c23e331bd41 +size 1229831200 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ2_XXS.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..bb65b7f --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:379263134944732fbf82cbb1a1809509e4f32be224eee43a6178637a80b65df6 +size 1146862624 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ3_M.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..0bb79a5 --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb603afc8d2fd19f7c32e69a0ecdc271459ca993d51dcfe79b9e0b51d19a0166 +size 1768967200 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ3_S.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..f6c4b71 --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:819fdda40a3f133a192f31210d43f713fe9035b0d334a7deba55cb6759ae85e8 +size 1712147488 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ3_XS.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..6be5b09 --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e35aaf589dbe15c5497a3bcd470c966bd85c5528bf0fc02677c30eaa8ee63e4 +size 1646087200 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ3_XXS.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..3ad7ffe --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cbe3f796cebaa9de572169fceb2ca33558902dde24d2d90ac43da215b9d32ac +size 1518064672 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ4_NL.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ4_NL.gguf new file mode 100644 index 0000000..f6db344 --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b502ba97ea6767c1b04c33b909405a897054f9de7d0a6a3accade478a830e343 +size 2138817568 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ4_XS.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..1d45c37 --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0ce71cd359a09f8a0e22282569e46e2289e18c833746b4b675ef0f2ce616d63 +size 2038424608 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q2_K.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..61dfd60 --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10d2c542b289bb9654049a0214a978f104c698917f68c6d98815e1c8d811a2be +size 1493218336 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q2_K_S.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..e4c0656 --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee970f5614a8e6d71ce931d48e22835dc28a4c77b7cfb565a136e00cf507593d +size 1403565088 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q3_K_L.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..6582694 --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b0f911a5c5a2566a4b1a7ed91830b3e485a461bb5313208a6412499ea612250 +size 1984646176 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q3_K_M.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..cb45a7a --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81eab2c8a1b40918aa0f62b0c7833b1696dab37a14688b8790f0e5e60b8f6705 +size 1856457760 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q3_K_S.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..f95dcb2 --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:795734b006fc4d67ed34b60f122f8be865e131e1924cfa6d4e55870e5b193167 +size 1712147488 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q4_0.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..477bf42 --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07b090236eb1b8cd0cbac128fb209cd3c95d85d572e10548d87c2714aaa67eb4 +size 2143536160 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q4_1.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q4_1.gguf new file mode 100644 index 0000000..706d086 --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:205bc6843653cc5f52edcd83083be22f8447786d51d947f6cbe7db67dfebd23a +size 2339603488 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q4_K_M.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..a15db7f --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d2fd8eb71e8e1f066827c308eed5727497c34e98ce6a688bff5fa32fb1d9f68 +size 2241004576 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q4_K_S.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..f33033a --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7911fe0b647efae73d29ff37f15598209077144ec5904a8483693310a585781 +size 2149827616 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q5_K_M.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..d7aa533 --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:967a9db70f356cb00de10395c1efd3e36ba98e7a8692febb2bfbf16188efbd54 +size 2593031200 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q5_K_S.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..a1a94a1 --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eac07d3407e53110ec1929fbd4ab378a8216c9170522eef8ff2d8a56f20363b1 +size 2540389408 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q6_K.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..8626331 --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95a6c0eecfae6bb379c4968a632ac8875da2505d4819dc81635438f1df7893d2 +size 2967059488 diff --git a/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.imatrix.gguf b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.imatrix.gguf new file mode 100644 index 0000000..ca0605c --- /dev/null +++ b/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cf4881260109f6036cd68ac1f2586c937216b3725736207035597b689cd290c +size 3012064 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c2eae81 --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: ytz20/GAD-GPT-5-Chat-Llama-3.2-3B-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-Llama-3.2-3B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-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-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 1.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 1.6 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 1.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.1 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.2 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 2.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q4_1.gguf) | i1-Q4_1 | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 3.1 | 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. + +