commit bef1e63dd375d5b6f84961b712e2d20e5f1714c8 Author: ModelHub XC Date: Mon Jun 15 03:52:16 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/CirtusMandarin-14B-test2-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ee3795a --- /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 +CirtusMandarin-14B-test2.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +CirtusMandarin-14B-test2.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CirtusMandarin-14B-test2.i1-IQ1_M.gguf b/CirtusMandarin-14B-test2.i1-IQ1_M.gguf new file mode 100644 index 0000000..dfab8ff --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:534dc76d33b52325ff45922ad9113e4dca72c5e8f263ba242c14abdcaae21a4e +size 3848262464 diff --git a/CirtusMandarin-14B-test2.i1-IQ1_S.gguf b/CirtusMandarin-14B-test2.i1-IQ1_S.gguf new file mode 100644 index 0000000..c20de44 --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dbde4ba995cc4e95b8dce9cd6e5bd434de584dbe5f1902a5df6c508f1b3462b +size 3578540864 diff --git a/CirtusMandarin-14B-test2.i1-IQ2_M.gguf b/CirtusMandarin-14B-test2.i1-IQ2_M.gguf new file mode 100644 index 0000000..c49f47a --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05c8c2be7e3342999339fdbba0bfca2582c13eedc15c53dc7ea2d8ccfc783510 +size 5321408736 diff --git a/CirtusMandarin-14B-test2.i1-IQ2_S.gguf b/CirtusMandarin-14B-test2.i1-IQ2_S.gguf new file mode 100644 index 0000000..b284a9d --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7947240fd60e3c2c6751ebd276a7ff25f43a08f30b9192d44d8e53a6a637a11 +size 4961779936 diff --git a/CirtusMandarin-14B-test2.i1-IQ2_XS.gguf b/CirtusMandarin-14B-test2.i1-IQ2_XS.gguf new file mode 100644 index 0000000..fd50bd4 --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f78783dffb2be5595e550728c6d512c221f2f4a8c0470d7798737e76bd5ed926 +size 4690195264 diff --git a/CirtusMandarin-14B-test2.i1-IQ2_XXS.gguf b/CirtusMandarin-14B-test2.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..b0fe2d5 --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13ea7acafda4c7343748da57963e96111152d2b2acce698bc3fb60f937222fc8 +size 4297798464 diff --git a/CirtusMandarin-14B-test2.i1-IQ3_M.gguf b/CirtusMandarin-14B-test2.i1-IQ3_M.gguf new file mode 100644 index 0000000..ee56232 --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99d391f82ba938b332e77c4c2e2bf7a242a2bbb3db9a057a264ae021f36a0a6a +size 6881695680 diff --git a/CirtusMandarin-14B-test2.i1-IQ3_S.gguf b/CirtusMandarin-14B-test2.i1-IQ3_S.gguf new file mode 100644 index 0000000..ab43ab6 --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26e278e1229080d6c11d6b29bafcdf762f0b4fab32f171f8fdb561d02691a0a3 +size 6683244480 diff --git a/CirtusMandarin-14B-test2.i1-IQ3_XS.gguf b/CirtusMandarin-14B-test2.i1-IQ3_XS.gguf new file mode 100644 index 0000000..bd916c6 --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16e8395e68eaeb6865a2408730980fa61199e496b9ab2f6c2c1d8616118b4d5e +size 6373586880 diff --git a/CirtusMandarin-14B-test2.i1-IQ3_XXS.gguf b/CirtusMandarin-14B-test2.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..c950109 --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:001f95b7c71d2452feaf2afd31ba02bdb7232ead9e29585abcad9a41486f591b +size 5941133536 diff --git a/CirtusMandarin-14B-test2.i1-IQ4_NL.gguf b/CirtusMandarin-14B-test2.i1-IQ4_NL.gguf new file mode 100644 index 0000000..d3ce967 --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:287239ef0a48becbc856867f840749acb7083e27acb8be9a7b2da6b6952aec6f +size 8539467392 diff --git a/CirtusMandarin-14B-test2.i1-IQ4_XS.gguf b/CirtusMandarin-14B-test2.i1-IQ4_XS.gguf new file mode 100644 index 0000000..5e7a336 --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50c11ad5d1b10c61d08bbde9f286a4f98b05e5d04cbddeb1868cfd391e02ec14 +size 8108877152 diff --git a/CirtusMandarin-14B-test2.i1-Q2_K.gguf b/CirtusMandarin-14B-test2.i1-Q2_K.gguf new file mode 100644 index 0000000..d7132e7 --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e1f725f3ab2f8a6d223f07d8b0fb4561b3a7d90339f77d267660f3eadfa0b5c +size 5752408608 diff --git a/CirtusMandarin-14B-test2.i1-Q2_K_S.gguf b/CirtusMandarin-14B-test2.i1-Q2_K_S.gguf new file mode 100644 index 0000000..6ec1f75 --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20820d2d418f2d10601cccf71ef6b9a1321c45304498c62053cea9e6bda831a1 +size 5388274208 diff --git a/CirtusMandarin-14B-test2.i1-Q3_K_L.gguf b/CirtusMandarin-14B-test2.i1-Q3_K_L.gguf new file mode 100644 index 0000000..1dde432 --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db900333b7262d501b0632b1aed5620ba622e1be89d22debece8b67754d29df4 +size 7898937280 diff --git a/CirtusMandarin-14B-test2.i1-Q3_K_M.gguf b/CirtusMandarin-14B-test2.i1-Q3_K_M.gguf new file mode 100644 index 0000000..21ab1ab --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8893616367cb9c3c561d6f982613bf356583d5acfaca923d25d3008f941f866d +size 7319599040 diff --git a/CirtusMandarin-14B-test2.i1-Q3_K_S.gguf b/CirtusMandarin-14B-test2.i1-Q3_K_S.gguf new file mode 100644 index 0000000..8e89320 --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a374fb542f4f877161ef1c66ef2414842ab70f35999f621283cd2bd8d391495 +size 6655391680 diff --git a/CirtusMandarin-14B-test2.i1-Q4_0.gguf b/CirtusMandarin-14B-test2.i1-Q4_0.gguf new file mode 100644 index 0000000..6275f99 --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad0e17cb5a64dd869911ffd5c0fc225ef8dfc650cf0ca1c27d0ca605c0518fd7 +size 8541105792 diff --git a/CirtusMandarin-14B-test2.i1-Q4_1.gguf b/CirtusMandarin-14B-test2.i1-Q4_1.gguf new file mode 100644 index 0000000..2c6b9b6 --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36480908c4b63964a79049aed4da2b315401590272b4a38df6a098ad45278a64 +size 9387540672 diff --git a/CirtusMandarin-14B-test2.i1-Q4_K_M.gguf b/CirtusMandarin-14B-test2.i1-Q4_K_M.gguf new file mode 100644 index 0000000..427a877 --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76e84dad6a9f2d73c06a91790130c2316c868184f6d18edade3ebe88ea3a70c5 +size 8999857792 diff --git a/CirtusMandarin-14B-test2.i1-Q4_K_S.gguf b/CirtusMandarin-14B-test2.i1-Q4_K_S.gguf new file mode 100644 index 0000000..25b4712 --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96ac3e05668e5f6a06fc13ce49ee5ef47f901b12a755fc5364dda4179cd835f2 +size 8571580032 diff --git a/CirtusMandarin-14B-test2.i1-Q5_K_M.gguf b/CirtusMandarin-14B-test2.i1-Q5_K_M.gguf new file mode 100644 index 0000000..6deaeeb --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c77321cf990de9de7b28af57c3f98f2a6539ac9c669b35dd4b5a412041b6a1c +size 10512503552 diff --git a/CirtusMandarin-14B-test2.i1-Q5_K_S.gguf b/CirtusMandarin-14B-test2.i1-Q5_K_S.gguf new file mode 100644 index 0000000..838a679 --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a65c056f1a3a77a6551a30d4d92c53406cda773716b11ce8848b214683449f7f +size 10261828352 diff --git a/CirtusMandarin-14B-test2.i1-Q6_K.gguf b/CirtusMandarin-14B-test2.i1-Q6_K.gguf new file mode 100644 index 0000000..7136ad5 --- /dev/null +++ b/CirtusMandarin-14B-test2.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c687252ec6380ed028f327715094ecd42f238a5eec7dc1e3fb15006daab7ce3 +size 12119689696 diff --git a/CirtusMandarin-14B-test2.imatrix.gguf b/CirtusMandarin-14B-test2.imatrix.gguf new file mode 100644 index 0000000..110be4f --- /dev/null +++ b/CirtusMandarin-14B-test2.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3755d27669bdc0780e5be09bed61ef2c1eddf5d39ddad8b68a77d4367873fb16 +size 7743552 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3a0390e --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: DoppelReflEx/CirtusMandarin-14B-test2 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/DoppelReflEx/CirtusMandarin-14B-test2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#CirtusMandarin-14B-test2-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-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/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-IQ1_S.gguf) | i1-IQ1_S | 3.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-IQ1_M.gguf) | i1-IQ1_M | 3.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-IQ2_S.gguf) | i1-IQ2_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-IQ2_M.gguf) | i1-IQ2_M | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-IQ4_NL.gguf) | i1-IQ4_NL | 8.6 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-Q4_1.gguf) | i1-Q4_1 | 9.5 | | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/CirtusMandarin-14B-test2-i1-GGUF/resolve/main/CirtusMandarin-14B-test2.i1-Q6_K.gguf) | i1-Q6_K | 12.2 | 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. + +