commit 2a4db610318eb1eeaf59e90d4f2ca5142b7c3cb3 Author: ModelHub XC Date: Fri Oct 9 11:10:27 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..071a6ef --- /dev/null +++ b/.gitattributes @@ -0,0 +1,65 @@ +*.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 +Qwen2.5-1.5B-Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-1.5B-Instruct.i1-IQ1_M.gguf b/Qwen2.5-1.5B-Instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..99d3978 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b88721f6033d5aabe313cae4e79bff027801cd5345e1db226a757d4b526be690 +size 464461984 diff --git a/Qwen2.5-1.5B-Instruct.i1-IQ1_S.gguf b/Qwen2.5-1.5B-Instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..aa6036c --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe327fc87dcf19f691aa140537ddc494168737d96c949efa1ff2fb0baa7fd385 +size 436528288 diff --git a/Qwen2.5-1.5B-Instruct.i1-IQ2_M.gguf b/Qwen2.5-1.5B-Instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..45b971e --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28bbb44160baede7b17f9d6d3789e07135c5261cd42c0891ab78520facb5ebb5 +size 601055392 diff --git a/Qwen2.5-1.5B-Instruct.i1-IQ2_S.gguf b/Qwen2.5-1.5B-Instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..4552aa0 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1e8f87db2276056d7eeb6c4bc1a0ffca01ffe5fc1521c0137e66b1898cee980 +size 563810464 diff --git a/Qwen2.5-1.5B-Instruct.i1-IQ2_XS.gguf b/Qwen2.5-1.5B-Instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..bce2f60 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:306bbfa590c974c94ffcb81134cbfc390e31fb6f3815eb2dd26317f29f25fbb3 +size 550327456 diff --git a/Qwen2.5-1.5B-Instruct.i1-IQ2_XXS.gguf b/Qwen2.5-1.5B-Instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..14eb85e --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20f98130d5656b439e2a977b69288a5d178bb8d252db7416ec450a073ce77754 +size 511018144 diff --git a/Qwen2.5-1.5B-Instruct.i1-IQ3_M.gguf b/Qwen2.5-1.5B-Instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..9a9fa05 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40971edfa84e426d05d75131800c8e6cc8e644ad4a9fab7ac26027ddc1a06c5c +size 776664736 diff --git a/Qwen2.5-1.5B-Instruct.i1-IQ3_S.gguf b/Qwen2.5-1.5B-Instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..9579bc6 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff047cabd8ac5aad125f243c347283ada7921b30938095f851ee5ea0a4e4d05f +size 762407584 diff --git a/Qwen2.5-1.5B-Instruct.i1-IQ3_XS.gguf b/Qwen2.5-1.5B-Instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..b58a706 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd06abcd27735825d33b87c88e61b2ef607bf8ec3f9225a0fd4d8327f12380b3 +size 731699872 diff --git a/Qwen2.5-1.5B-Instruct.i1-IQ3_XXS.gguf b/Qwen2.5-1.5B-Instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..b186cf0 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e32a2169bdd23ee93ee254cd9ebecb734dd8f3e12542e1a9a9a8893c974bfc0 +size 668792992 diff --git a/Qwen2.5-1.5B-Instruct.i1-IQ4_NL.gguf b/Qwen2.5-1.5B-Instruct.i1-IQ4_NL.gguf new file mode 100644 index 0000000..039a13b --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c156c655d2519b8f6034142f4a33f687e227fd67f64e1a29f7daecb7d8cb42d +size 936331936 diff --git a/Qwen2.5-1.5B-Instruct.i1-IQ4_XS.gguf b/Qwen2.5-1.5B-Instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..9c0a460 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bde05ad54f7de129f6bd39d49db703187564bac131401634ff3351406d7847f +size 895732384 diff --git a/Qwen2.5-1.5B-Instruct.i1-Q2_K.gguf b/Qwen2.5-1.5B-Instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..fdc9f68 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7149922841eb8d5af565d13124ba7deb88faf433468af302ca7985d3146dffd0 +size 676305568 diff --git a/Qwen2.5-1.5B-Instruct.i1-Q2_K_S.gguf b/Qwen2.5-1.5B-Instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..7f47e56 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a61cb14c5f6962991cbbe89a1c38810641698dc486406f382a76a2bd2594664 +size 640135840 diff --git a/Qwen2.5-1.5B-Instruct.i1-Q3_K_L.gguf b/Qwen2.5-1.5B-Instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..ce59627 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1040c00e7ebaf5e74e1f48122a3b91d48b026d2670834143000054055d2e6d7 +size 880163488 diff --git a/Qwen2.5-1.5B-Instruct.i1-Q3_K_M.gguf b/Qwen2.5-1.5B-Instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..b3038c9 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96d66b1deb0f351d074bc7088b507e9825a008c28aff3d4ba6e20ea016990f9f +size 824179360 diff --git a/Qwen2.5-1.5B-Instruct.i1-Q3_K_S.gguf b/Qwen2.5-1.5B-Instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..e47b71e --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78f3a330ff893aac589002a4dd6a267d01edb7643fb4d7ed3e3869a3e9b30192 +size 760945312 diff --git a/Qwen2.5-1.5B-Instruct.i1-Q4_0.gguf b/Qwen2.5-1.5B-Instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..73463f1 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2991f24c60c2e722759c21ad1f091093d144a93f37ff06f4369bbc165a1fb96b +size 937536160 diff --git a/Qwen2.5-1.5B-Instruct.i1-Q4_0_4_4.gguf b/Qwen2.5-1.5B-Instruct.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..0413f36 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92a010b6ed270ff41730003b5aab235cbbf111dbbc469eabc426bb79661e3c0c +size 934955680 diff --git a/Qwen2.5-1.5B-Instruct.i1-Q4_0_4_8.gguf b/Qwen2.5-1.5B-Instruct.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..1bad063 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdf12244e8e17d58aa83d2023ea655a4ff6c5abdf4f6e56a4977dc6b7b077436 +size 934955680 diff --git a/Qwen2.5-1.5B-Instruct.i1-Q4_0_8_8.gguf b/Qwen2.5-1.5B-Instruct.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..e9d1062 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:860bffa6cde03b2a93c7776cbb3ee4988c4aa01d85b7a54399d43add79dd00c8 +size 934955680 diff --git a/Qwen2.5-1.5B-Instruct.i1-Q4_1.gguf b/Qwen2.5-1.5B-Instruct.i1-Q4_1.gguf new file mode 100644 index 0000000..31fb33c --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d542c7ff06cfa8328e6dc3e325ec444ac5e6efb4fc46c22bd79d73e09ee966c6 +size 1016842912 diff --git a/Qwen2.5-1.5B-Instruct.i1-Q4_K_M.gguf b/Qwen2.5-1.5B-Instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..bdf293a --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7521392b4a648dcfc01ad649defbb41841bfd43acbd1ed1c807923ba55d7ccf8 +size 986049184 diff --git a/Qwen2.5-1.5B-Instruct.i1-Q4_K_S.gguf b/Qwen2.5-1.5B-Instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..84d230c --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad25f91e1cc9bcad5a0f59f014ffd8631aebbfe28201de5a09186c98d59e59e6 +size 940313248 diff --git a/Qwen2.5-1.5B-Instruct.i1-Q5_0.gguf b/Qwen2.5-1.5B-Instruct.i1-Q5_0.gguf new file mode 100644 index 0000000..a337527 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2a7d4c00f3e7b48d65e1689fc5a4fac9ee536c729a61a42d477264e9a218963 +size 1101310624 diff --git a/Qwen2.5-1.5B-Instruct.i1-Q5_1.gguf b/Qwen2.5-1.5B-Instruct.i1-Q5_1.gguf new file mode 100644 index 0000000..1d3fd3d --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:369ced29e6dd36a774e1b765b207a6de88b0dfdd795ac3788e6a8b06f4512487 +size 1180617376 diff --git a/Qwen2.5-1.5B-Instruct.i1-Q5_K_M.gguf b/Qwen2.5-1.5B-Instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..560726b --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:764e27f6c6b89b0a71bf1feac81044c1f6b939aadab3da99980f5cced2c779a9 +size 1125051040 diff --git a/Qwen2.5-1.5B-Instruct.i1-Q5_K_S.gguf b/Qwen2.5-1.5B-Instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..0677c8a --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bfca8f8c218730f80ee67766e1f662f1a0a7084bef765be63f1eb897c009da7 +size 1098730144 diff --git a/Qwen2.5-1.5B-Instruct.i1-Q6_K.gguf b/Qwen2.5-1.5B-Instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..525b193 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50aac43dcd3b950caf94476a74aea799c9877f44c3496b8ce5424df62bb5d3da +size 1272740512 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0f75772 --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: Qwen/Qwen2.5-1.5B-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct/blob/main/LICENSE +quantized_by: mradermacher +tags: +- chat +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct + + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-1.5B-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/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 0.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 0.6 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 0.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.9 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 0.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 1.0 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 1.0 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 1.0 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 1.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-Q4_1.gguf) | i1-Q4_1 | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-Q5_0.gguf) | i1-Q5_0 | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-Q5_1.gguf) | i1-Q5_1 | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-1.5B-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 1.4 | 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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..9d83fd0 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:606ec9dd36c14f932ff9294399db775391fb6913a51d0b11e0eceee588145dfb +size 2042201