commit 1826f7edee010adafe8161c8d74c0fd4f3663e00 Author: ModelHub XC Date: Mon Sep 28 10:41:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3984f84 --- /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 +Qwen1.5-1.8B-Chat.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen1.5-1.8B-Chat.i1-IQ1_M.gguf b/Qwen1.5-1.8B-Chat.i1-IQ1_M.gguf new file mode 100644 index 0000000..63452f7 --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c1dbd4a6d03e99b2d065b7b8a131aa7b9014f3e1240e97cf90e6474df1657d2 +size 696519808 diff --git a/Qwen1.5-1.8B-Chat.i1-IQ1_S.gguf b/Qwen1.5-1.8B-Chat.i1-IQ1_S.gguf new file mode 100644 index 0000000..8b18de5 --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:397397f932a6b50b71948617598160a4b1d2a4d8383356aa25b218a0d332ba49 +size 679120000 diff --git a/Qwen1.5-1.8B-Chat.i1-IQ2_M.gguf b/Qwen1.5-1.8B-Chat.i1-IQ2_M.gguf new file mode 100644 index 0000000..275d985 --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5710538cf8ad04172ef15ddf5f3092aaa67daea50da7ab8254cfc76479a05a1 +size 831046784 diff --git a/Qwen1.5-1.8B-Chat.i1-IQ2_S.gguf b/Qwen1.5-1.8B-Chat.i1-IQ2_S.gguf new file mode 100644 index 0000000..a141e06 --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e55f263e1f9c187be0d2e55429e12f62d185015e0d03d4a5b43ae1a628672a0 +size 807847040 diff --git a/Qwen1.5-1.8B-Chat.i1-IQ2_XS.gguf b/Qwen1.5-1.8B-Chat.i1-IQ2_XS.gguf new file mode 100644 index 0000000..d0f7273 --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d3dfbca295e873d65ba933ca136a3bea4d6f9d69e06dd754a670009534a42f9 +size 751864960 diff --git a/Qwen1.5-1.8B-Chat.i1-IQ2_XXS.gguf b/Qwen1.5-1.8B-Chat.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..e9787b9 --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f148692ea4f94433f8e82b1f747f38d41f7a4060dbdbcf5243d997295ba6145 +size 725519488 diff --git a/Qwen1.5-1.8B-Chat.i1-IQ3_M.gguf b/Qwen1.5-1.8B-Chat.i1-IQ3_M.gguf new file mode 100644 index 0000000..3a7af31 --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbceeef638a486b03a5b7f7b90809ec40a1128632c743038551e2879e5adac7c +size 984538240 diff --git a/Qwen1.5-1.8B-Chat.i1-IQ3_S.gguf b/Qwen1.5-1.8B-Chat.i1-IQ3_S.gguf new file mode 100644 index 0000000..f24c361 --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d79c37992c224a8f44c47954e980e250b6527e4934266a4b1ae8c2223dc73d57 +size 953572480 diff --git a/Qwen1.5-1.8B-Chat.i1-IQ3_XS.gguf b/Qwen1.5-1.8B-Chat.i1-IQ3_XS.gguf new file mode 100644 index 0000000..61674d1 --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2615c607f0a7365f955b8b47b01c60785de3493f6f15e5fd509530ab33235dd9 +size 925113472 diff --git a/Qwen1.5-1.8B-Chat.i1-IQ3_XXS.gguf b/Qwen1.5-1.8B-Chat.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..d4998dc --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a895b74dca16713a4566b5e415c794607e88cfee4847f445ff7b0f8bcb9ae636 +size 860144768 diff --git a/Qwen1.5-1.8B-Chat.i1-IQ4_NL.gguf b/Qwen1.5-1.8B-Chat.i1-IQ4_NL.gguf new file mode 100644 index 0000000..adab97c --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a9c0aedca85e847c4de0ae80e53877b50b5028b03221359486889cb4546191e +size 1120236672 diff --git a/Qwen1.5-1.8B-Chat.i1-IQ4_XS.gguf b/Qwen1.5-1.8B-Chat.i1-IQ4_XS.gguf new file mode 100644 index 0000000..b2d09fc --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dac399aaa3608a0d4902adfe45d09bc336c1a58f1780e3d4ded00dbc61c90bc +size 1081021568 diff --git a/Qwen1.5-1.8B-Chat.i1-Q2_K.gguf b/Qwen1.5-1.8B-Chat.i1-Q2_K.gguf new file mode 100644 index 0000000..1caf86c --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18475ad9ba067cdb78cccce4f2f64cf0e259c25059b215e8cc8f89e7037e4aaa +size 846570624 diff --git a/Qwen1.5-1.8B-Chat.i1-Q2_K_S.gguf b/Qwen1.5-1.8B-Chat.i1-Q2_K_S.gguf new file mode 100644 index 0000000..64597e1 --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db1ac357a05b6bdfa93aa056e3ebf3a224452ac5c7d4d5e3b84d867d9f6e9c26 +size 830350464 diff --git a/Qwen1.5-1.8B-Chat.i1-Q3_K_L.gguf b/Qwen1.5-1.8B-Chat.i1-Q3_K_L.gguf new file mode 100644 index 0000000..aa3d039 --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae9465d35b588e0361e8a767e94928ab247619a915c0cab51fac29874c005393 +size 1056201856 diff --git a/Qwen1.5-1.8B-Chat.i1-Q3_K_M.gguf b/Qwen1.5-1.8B-Chat.i1-Q3_K_M.gguf new file mode 100644 index 0000000..56ea879 --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bda5dd9910f9be3b1f7624fa6c3d496a860ce25bac42dac7fbc761ba288b6092 +size 1015880832 diff --git a/Qwen1.5-1.8B-Chat.i1-Q3_K_S.gguf b/Qwen1.5-1.8B-Chat.i1-Q3_K_S.gguf new file mode 100644 index 0000000..250f7d0 --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:559215fa1ced9f625df2c48b056c6223d5dfe19ec1df65d3a28ba736cf24256d +size 953572480 diff --git a/Qwen1.5-1.8B-Chat.i1-Q4_0.gguf b/Qwen1.5-1.8B-Chat.i1-Q4_0.gguf new file mode 100644 index 0000000..867392a --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b62c09f8b0797f184fbd354988fea359fd700f200282bc3cf40331f16816514b +size 1122350208 diff --git a/Qwen1.5-1.8B-Chat.i1-Q4_1.gguf b/Qwen1.5-1.8B-Chat.i1-Q4_1.gguf new file mode 100644 index 0000000..b5797bc --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d62ffa259624101313b89cafed741f4029ebe90f07460a41dc05af4dd0b73594 +size 1215575168 diff --git a/Qwen1.5-1.8B-Chat.i1-Q4_K_M.gguf b/Qwen1.5-1.8B-Chat.i1-Q4_K_M.gguf new file mode 100644 index 0000000..059b7df --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8d2bde28ddb4648966f31507342e51d7305c4eacb684c3bd1cdaa4e83b613b6 +size 1217754240 diff --git a/Qwen1.5-1.8B-Chat.i1-Q4_K_S.gguf b/Qwen1.5-1.8B-Chat.i1-Q4_K_S.gguf new file mode 100644 index 0000000..e68ea0e --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0c35a2d1479fd6fb2891900743bd0570e7491b82292d942527ccaa676a0a9b3 +size 1158263936 diff --git a/Qwen1.5-1.8B-Chat.i1-Q5_K_M.gguf b/Qwen1.5-1.8B-Chat.i1-Q5_K_M.gguf new file mode 100644 index 0000000..6b6ac8a --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c694e451d8762101f284592b39da7918387f6db6500d7f1b259977a61a6e2715 +size 1376777344 diff --git a/Qwen1.5-1.8B-Chat.i1-Q5_K_S.gguf b/Qwen1.5-1.8B-Chat.i1-Q5_K_S.gguf new file mode 100644 index 0000000..7f30922 --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf4816f4c00fa307a444f5f7b3a5b20f6c00f2cdbc603e974ba12226c5e74b56 +size 1327821952 diff --git a/Qwen1.5-1.8B-Chat.i1-Q6_K.gguf b/Qwen1.5-1.8B-Chat.i1-Q6_K.gguf new file mode 100644 index 0000000..3e2fad2 --- /dev/null +++ b/Qwen1.5-1.8B-Chat.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c146e5a06f87682b49194b0852e099bd43016a219717ca8a5fdd9ce10ba05ea +size 1579027584 diff --git a/README.md b/README.md new file mode 100644 index 0000000..eb5ba7b --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: Qwen/Qwen1.5-1.8B-Chat +language: +- en +library_name: transformers +license: other +license_link: https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat/blob/main/LICENSE +license_name: tongyi-qianwen-research +quantized_by: mradermacher +tags: +- chat +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat + + +static quants are available at https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-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/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-IQ1_S.gguf) | i1-IQ1_S | 0.8 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-IQ1_M.gguf) | i1-IQ1_M | 0.8 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-IQ2_S.gguf) | i1-IQ2_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.9 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-IQ2_M.gguf) | i1-IQ2_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-Q2_K.gguf) | i1-Q2_K | 0.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-IQ3_S.gguf) | i1-IQ3_S | 1.1 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.1 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-IQ3_M.gguf) | i1-IQ3_M | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.2 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-Q4_0.gguf) | i1-Q4_0 | 1.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.3 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-Q4_1.gguf) | i1-Q4_1 | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-i1-GGUF/resolve/main/Qwen1.5-1.8B-Chat.i1-Q6_K.gguf) | i1-Q6_K | 1.7 | 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..7455ba2 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff05d4093e8c51049d5b57f299528b41f8fa5ce0b9447aa61c27285f639c34b0 +size 1713589