commit a9e57ee5d65843abbc3d60aadf08c858dddfef40 Author: ModelHub XC Date: Fri Jul 17 07:14:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7efae6d --- /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 +Qwen2.5-14B-Wernicke.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Wernicke.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-14B-Wernicke.i1-IQ1_M.gguf b/Qwen2.5-14B-Wernicke.i1-IQ1_M.gguf new file mode 100644 index 0000000..6dfba35 --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52fbb51da64991d0d955df5fb640b8a6ede53c583da709ac05f5f6ab9cbd1e43 +size 3872310720 diff --git a/Qwen2.5-14B-Wernicke.i1-IQ1_S.gguf b/Qwen2.5-14B-Wernicke.i1-IQ1_S.gguf new file mode 100644 index 0000000..88692ca --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95b482a404dfc8de9a640c78b03495eb29e1fff5557a4d6b9f7625bb953f6b60 +size 3607995840 diff --git a/Qwen2.5-14B-Wernicke.i1-IQ2_M.gguf b/Qwen2.5-14B-Wernicke.i1-IQ2_M.gguf new file mode 100644 index 0000000..eeb8f40 --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef1584155da7666641695e1787b2a8c7966d122a893a50160dac1fd536ae21fa +size 5356148160 diff --git a/Qwen2.5-14B-Wernicke.i1-IQ2_S.gguf b/Qwen2.5-14B-Wernicke.i1-IQ2_S.gguf new file mode 100644 index 0000000..5173f1c --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fa76314c40d0d1c54a08d5ac524955a9e80842538e0e4ec35d175deda4bb227 +size 5003728320 diff --git a/Qwen2.5-14B-Wernicke.i1-IQ2_XS.gguf b/Qwen2.5-14B-Wernicke.i1-IQ2_XS.gguf new file mode 100644 index 0000000..5a655e0 --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cc277adef67ed1a178e6ae229f3247fbc8a3357af2a34aed190b056e801582a +size 4704576960 diff --git a/Qwen2.5-14B-Wernicke.i1-IQ2_XXS.gguf b/Qwen2.5-14B-Wernicke.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..1236c51 --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:701dfa93e9f2a88bb3b21315e043ec2d7bb9f6d487d879901c5873e1c8c61ef0 +size 4312835520 diff --git a/Qwen2.5-14B-Wernicke.i1-IQ3_M.gguf b/Qwen2.5-14B-Wernicke.i1-IQ3_M.gguf new file mode 100644 index 0000000..c52adb6 --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15bfbba6444f9465be7c4c88f3cdda604da9f3532706575f3f10a05b9283aeed +size 6916539840 diff --git a/Qwen2.5-14B-Wernicke.i1-IQ3_S.gguf b/Qwen2.5-14B-Wernicke.i1-IQ3_S.gguf new file mode 100644 index 0000000..fe0517e --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91d7e05475903e2b2b147eea276aed25ebf68a3df32ec0a2a1fffa02def4443e +size 6693021120 diff --git a/Qwen2.5-14B-Wernicke.i1-IQ3_XS.gguf b/Qwen2.5-14B-Wernicke.i1-IQ3_XS.gguf new file mode 100644 index 0000000..a6a141a --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:878153502f886bb3b341e4d8d1fb1707d4980a90d80d840ecc6fa23e42e0c862 +size 6383363520 diff --git a/Qwen2.5-14B-Wernicke.i1-IQ3_XXS.gguf b/Qwen2.5-14B-Wernicke.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..294c26f --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc3ece00cf9759b59be8801485bcc36c014c93f3e266f8bb2c0e257bbd0028e6 +size 5946709440 diff --git a/Qwen2.5-14B-Wernicke.i1-IQ4_XS.gguf b/Qwen2.5-14B-Wernicke.i1-IQ4_XS.gguf new file mode 100644 index 0000000..8ce5c96 --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:400e2e795f0f58554bcf3e8011256fe59da42b9f764e3779cf10767f5b0750bf +size 8119842240 diff --git a/Qwen2.5-14B-Wernicke.i1-Q2_K.gguf b/Qwen2.5-14B-Wernicke.i1-Q2_K.gguf new file mode 100644 index 0000000..480ce08 --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d23c9d6dbb12280f64b46530fa68e8451e3a1c920edfab36aeb546ba7e8cec19 +size 5770499520 diff --git a/Qwen2.5-14B-Wernicke.i1-Q3_K_L.gguf b/Qwen2.5-14B-Wernicke.i1-Q3_K_L.gguf new file mode 100644 index 0000000..c521f10 --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df556917dfdadb3ab940fcd49b0204c8474375790219985dca16be56a3ca1aa2 +size 7924770240 diff --git a/Qwen2.5-14B-Wernicke.i1-Q3_K_M.gguf b/Qwen2.5-14B-Wernicke.i1-Q3_K_M.gguf new file mode 100644 index 0000000..dbfa555 --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71889727833bde9670686aa0ca9143cea1b3df8b739d04f9f1dc0af27056fb5c +size 7339206080 diff --git a/Qwen2.5-14B-Wernicke.i1-Q3_K_S.gguf b/Qwen2.5-14B-Wernicke.i1-Q3_K_S.gguf new file mode 100644 index 0000000..ae4334f --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:104b84265e3464080d5a5e74bb148bfed6bb1291cee340be460f3d416cee3407 +size 6659597760 diff --git a/Qwen2.5-14B-Wernicke.i1-Q4_0.gguf b/Qwen2.5-14B-Wernicke.i1-Q4_0.gguf new file mode 100644 index 0000000..bfb8745 --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e11241278839bb964625bde9bb307e1dd5d98047085a8a1aaeef3196e45cbd3 +size 8544269760 diff --git a/Qwen2.5-14B-Wernicke.i1-Q4_0_4_4.gguf b/Qwen2.5-14B-Wernicke.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..11decae --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26dfa65bc424745c0fd3a6f3815fdd7120efc0158a5faebac8d1b70297b1efa9 +size 8517727680 diff --git a/Qwen2.5-14B-Wernicke.i1-Q4_0_4_8.gguf b/Qwen2.5-14B-Wernicke.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..7ebc39b --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f956329e5dc6ad8aa298d22866a6c57bbe728efbf2a4c2452cfe7f79ffedcb98 +size 8517727680 diff --git a/Qwen2.5-14B-Wernicke.i1-Q4_0_8_8.gguf b/Qwen2.5-14B-Wernicke.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..e86dc5c --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5e6647ffb9ac598cecdabdde7b36cf6bc3dbbf58db338733cbcf1f6120ae565 +size 8517727680 diff --git a/Qwen2.5-14B-Wernicke.i1-Q4_K_M.gguf b/Qwen2.5-14B-Wernicke.i1-Q4_K_M.gguf new file mode 100644 index 0000000..2d71164 --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e2e181ed2043f5fd2915880b3f1938162d6d3d51d7f0d0200266c723cb9d71a +size 8988112320 diff --git a/Qwen2.5-14B-Wernicke.i1-Q4_K_S.gguf b/Qwen2.5-14B-Wernicke.i1-Q4_K_S.gguf new file mode 100644 index 0000000..b060b81 --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eabda70bea9a72babc9931888a4c1fb3738476f89f7f7d59038abb7583e85d9 +size 8573433280 diff --git a/Qwen2.5-14B-Wernicke.i1-Q5_K_M.gguf b/Qwen2.5-14B-Wernicke.i1-Q5_K_M.gguf new file mode 100644 index 0000000..2494dac --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:114bf62e574838c78b0fab67bba9c00a0296f0d8bdbde96864cb19ff1c5d9494 +size 10508875200 diff --git a/Qwen2.5-14B-Wernicke.i1-Q5_K_S.gguf b/Qwen2.5-14B-Wernicke.i1-Q5_K_S.gguf new file mode 100644 index 0000000..74d5798 --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f02233cd9d7836f3e9dc0d4676ce882c92687842260602ed0d8cc0ed58ebaeea +size 10266555840 diff --git a/Qwen2.5-14B-Wernicke.i1-Q6_K.gguf b/Qwen2.5-14B-Wernicke.i1-Q6_K.gguf new file mode 100644 index 0000000..b517fec --- /dev/null +++ b/Qwen2.5-14B-Wernicke.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1415747075de7facb6e185817513285896a4df540e0575472d56cd609208a4e +size 12124685760 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c1a65de --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: CultriX/Qwen2.5-14B-Wernicke +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/CultriX/Qwen2.5-14B-Wernicke + + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-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/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-IQ1_S.gguf) | i1-IQ1_S | 3.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-IQ1_M.gguf) | i1-IQ1_M | 4.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-IQ2_S.gguf) | i1-IQ2_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-IQ2_M.gguf) | i1-IQ2_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 8.6 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 8.6 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 8.6 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Wernicke-i1-GGUF/resolve/main/Qwen2.5-14B-Wernicke.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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..4cb615a --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f7cc7718db3d07cb45033b0d8b9136c8661a53b7d13a370a11779bf2d8711e7 +size 8563597