commit 6525195ff1292bf11caf771e73a406ce4ab4d07b Author: ModelHub XC Date: Sat Jul 25 12:21:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GRM-Kerlin-3b-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..151ed02 --- /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 +GRM-Kerlin-3b.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRM-Kerlin-3b.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GRM-Kerlin-3b.i1-IQ1_M.gguf b/GRM-Kerlin-3b.i1-IQ1_M.gguf new file mode 100644 index 0000000..4a4aa40 --- /dev/null +++ b/GRM-Kerlin-3b.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b9a666cc24626ac73b610571f9fb7a5deb5d23d27b95d4a296ce51c42f6e87d +size 952128736 diff --git a/GRM-Kerlin-3b.i1-IQ1_S.gguf b/GRM-Kerlin-3b.i1-IQ1_S.gguf new file mode 100644 index 0000000..ba58af3 --- /dev/null +++ b/GRM-Kerlin-3b.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21c6cf0adef4f72b8182d7a1aedf73fbdef5d656a1271313ce2ce5c10a008e71 +size 893195488 diff --git a/GRM-Kerlin-3b.i1-IQ2_M.gguf b/GRM-Kerlin-3b.i1-IQ2_M.gguf new file mode 100644 index 0000000..df2ccd1 --- /dev/null +++ b/GRM-Kerlin-3b.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60b83b355507d0ff2e3d390b73e837d8c5b6b2f7dcc99bcb3a9b45bc600becce +size 1274219744 diff --git a/GRM-Kerlin-3b.i1-IQ2_S.gguf b/GRM-Kerlin-3b.i1-IQ2_S.gguf new file mode 100644 index 0000000..e7316e1 --- /dev/null +++ b/GRM-Kerlin-3b.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25adb17db6414f39030794e8a3f5b6756b3d04d125392bceea48399a7c08dd5c +size 1195642080 diff --git a/GRM-Kerlin-3b.i1-IQ2_XS.gguf b/GRM-Kerlin-3b.i1-IQ2_XS.gguf new file mode 100644 index 0000000..acce648 --- /dev/null +++ b/GRM-Kerlin-3b.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5ef9c84e0e9b4c61f4af66aa6407462db2adfb18192f3518b1073784161e696 +size 1133647072 diff --git a/GRM-Kerlin-3b.i1-IQ2_XXS.gguf b/GRM-Kerlin-3b.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..c22b1c5 --- /dev/null +++ b/GRM-Kerlin-3b.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c7b1af33136271bce73e9b4078b16fcdc21644fb8b6d786e934602cf09e4754 +size 1050350816 diff --git a/GRM-Kerlin-3b.i1-IQ3_M.gguf b/GRM-Kerlin-3b.i1-IQ3_M.gguf new file mode 100644 index 0000000..15ad47d --- /dev/null +++ b/GRM-Kerlin-3b.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ee228701c58a6b8290b724286501c773897241224f05bac05119492bf28c05e +size 1622598880 diff --git a/GRM-Kerlin-3b.i1-IQ3_S.gguf b/GRM-Kerlin-3b.i1-IQ3_S.gguf new file mode 100644 index 0000000..178ed56 --- /dev/null +++ b/GRM-Kerlin-3b.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3cbc5f6f838e45cdabeea2200e1384d86d16d145eb730bab84f04cd77b543fd +size 1590568160 diff --git a/GRM-Kerlin-3b.i1-IQ3_XS.gguf b/GRM-Kerlin-3b.i1-IQ3_XS.gguf new file mode 100644 index 0000000..71cccd6 --- /dev/null +++ b/GRM-Kerlin-3b.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66be94d69b65f75a9afa3746a3216e28252f1486174b543b7037851ad4317396 +size 1525540064 diff --git a/GRM-Kerlin-3b.i1-IQ3_XXS.gguf b/GRM-Kerlin-3b.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..415e100 --- /dev/null +++ b/GRM-Kerlin-3b.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:657f593424b80a8777cdec7d28f33eb4b149d8c17412baf4ab5caabb7e216f0c +size 1416531168 diff --git a/GRM-Kerlin-3b.i1-IQ4_NL.gguf b/GRM-Kerlin-3b.i1-IQ4_NL.gguf new file mode 100644 index 0000000..f4230c2 --- /dev/null +++ b/GRM-Kerlin-3b.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b573817802c754012913a00732b84655abc25eab6d9886c7eda5fbe36db7902 +size 2000239840 diff --git a/GRM-Kerlin-3b.i1-IQ4_XS.gguf b/GRM-Kerlin-3b.i1-IQ4_XS.gguf new file mode 100644 index 0000000..dd7c8d8 --- /dev/null +++ b/GRM-Kerlin-3b.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4800f04fea2a1b99f51bca8c8be5ca9917eada12a7d2b2373e3a010a5868a3c +size 1904401632 diff --git a/GRM-Kerlin-3b.i1-Q2_K.gguf b/GRM-Kerlin-3b.i1-Q2_K.gguf new file mode 100644 index 0000000..181e268 --- /dev/null +++ b/GRM-Kerlin-3b.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:412c90c664eda485a12f4e26c2c11acb853b8bae09ec6e1e35d4c6f7a5e175b7 +size 1376857312 diff --git a/GRM-Kerlin-3b.i1-Q2_K_S.gguf b/GRM-Kerlin-3b.i1-Q2_K_S.gguf new file mode 100644 index 0000000..052ac0d --- /dev/null +++ b/GRM-Kerlin-3b.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89985e827e3a18da18e189bb0d87253c248bf87785cf1169486f09fff2419d41 +size 1300229344 diff --git a/GRM-Kerlin-3b.i1-Q3_K_L.gguf b/GRM-Kerlin-3b.i1-Q3_K_L.gguf new file mode 100644 index 0000000..423acb2 --- /dev/null +++ b/GRM-Kerlin-3b.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:054cd1199dedd9a765408de47d611a0c1685777ff79b425804af945a66a932ad +size 1841095904 diff --git a/GRM-Kerlin-3b.i1-Q3_K_M.gguf b/GRM-Kerlin-3b.i1-Q3_K_M.gguf new file mode 100644 index 0000000..45d4f8c --- /dev/null +++ b/GRM-Kerlin-3b.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc2ea9bc1e0d5eb71109cf7079a367921c8bab7c1365b90ad7bbfb0e6b7e6369 +size 1724179680 diff --git a/GRM-Kerlin-3b.i1-Q3_K_S.gguf b/GRM-Kerlin-3b.i1-Q3_K_S.gguf new file mode 100644 index 0000000..2b853da --- /dev/null +++ b/GRM-Kerlin-3b.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0a4c683b07addf346dee08860a72cb22a762fb19f9c686ac54999d6bca69d24 +size 1588061408 diff --git a/GRM-Kerlin-3b.i1-Q4_0.gguf b/GRM-Kerlin-3b.i1-Q4_0.gguf new file mode 100644 index 0000000..77dd332 --- /dev/null +++ b/GRM-Kerlin-3b.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f59d8415114724c90de04332de3508f815627a9c6008295b7df8bdfaef70042e +size 2003516640 diff --git a/GRM-Kerlin-3b.i1-Q4_1.gguf b/GRM-Kerlin-3b.i1-Q4_1.gguf new file mode 100644 index 0000000..5262abc --- /dev/null +++ b/GRM-Kerlin-3b.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e72edc3ffd10a9fb5fe8c26c068035eee88c4c883656078ee654cd017f0581f +size 2190736608 diff --git a/GRM-Kerlin-3b.i1-Q4_K_M.gguf b/GRM-Kerlin-3b.i1-Q4_K_M.gguf new file mode 100644 index 0000000..65ab79b --- /dev/null +++ b/GRM-Kerlin-3b.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43a1fa211017212e455895d10d54e669f0692fb29fe1f8a72c8c58dc0947435a +size 2104933600 diff --git a/GRM-Kerlin-3b.i1-Q4_K_S.gguf b/GRM-Kerlin-3b.i1-Q4_K_S.gguf new file mode 100644 index 0000000..2e9c63c --- /dev/null +++ b/GRM-Kerlin-3b.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fae3e361e165d13b112bc98284e2d18954124cd9a26476059f9474516daec013 +size 2009414880 diff --git a/GRM-Kerlin-3b.i1-Q5_K_M.gguf b/GRM-Kerlin-3b.i1-Q5_K_M.gguf new file mode 100644 index 0000000..82e23e8 --- /dev/null +++ b/GRM-Kerlin-3b.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70edf4948b212e9715ab02a2d951d6b41fe2029dcf5d22d528f8c13926120661 +size 2438741216 diff --git a/GRM-Kerlin-3b.i1-Q5_K_S.gguf b/GRM-Kerlin-3b.i1-Q5_K_S.gguf new file mode 100644 index 0000000..105fd1e --- /dev/null +++ b/GRM-Kerlin-3b.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de38a358ba37a61251969ce67e9314c845a6795dd89ff9fbd7d7fa8a9c09edd7 +size 2383592672 diff --git a/GRM-Kerlin-3b.i1-Q6_K.gguf b/GRM-Kerlin-3b.i1-Q6_K.gguf new file mode 100644 index 0000000..43b7732 --- /dev/null +++ b/GRM-Kerlin-3b.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1f7c26c4c08d703215d6ddec443b55f9132f4da106d3a3ca56a3314cd7d4f64 +size 2793411808 diff --git a/GRM-Kerlin-3b.imatrix.gguf b/GRM-Kerlin-3b.imatrix.gguf new file mode 100644 index 0000000..87d87ea --- /dev/null +++ b/GRM-Kerlin-3b.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe11a36bc665c698c12b05bf15d38e5568bb68493a9e5b340143cc7dc044eae6 +size 3393408 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5f28075 --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: OrionLLM/GRM-Kerlin-3b +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/OrionLLM/GRM-Kerlin-3b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GRM-Kerlin-3b-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/GRM-Kerlin-3b-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/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-IQ1_M.gguf) | i1-IQ1_M | 1.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-IQ2_M.gguf) | i1-IQ2_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.7 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-IQ3_S.gguf) | i1-IQ3_S | 1.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.1 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-Q4_0.gguf) | i1-Q4_0 | 2.1 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.1 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-Q4_1.gguf) | i1-Q4_1 | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/GRM-Kerlin-3b-i1-GGUF/resolve/main/GRM-Kerlin-3b.i1-Q6_K.gguf) | i1-Q6_K | 2.9 | 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. + +