commit 55ffa94c7a39099226f34db3683d57f65bf9e454 Author: ModelHub XC Date: Mon May 11 14:33:43 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ffd1a72 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +GaMS-27B-Instruct-Nemotron.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +GaMS-27B-Instruct-Nemotron.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GaMS-27B-Instruct-Nemotron.i1-IQ1_M.gguf b/GaMS-27B-Instruct-Nemotron.i1-IQ1_M.gguf new file mode 100644 index 0000000..92d9017 --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:640090829021fb842e6c030ec75df672918b26dc6c5eb1ba41137ab1b89bae9c +size 6692471712 diff --git a/GaMS-27B-Instruct-Nemotron.i1-IQ1_S.gguf b/GaMS-27B-Instruct-Nemotron.i1-IQ1_S.gguf new file mode 100644 index 0000000..fb90a4c --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf51228d7757a8d7261c798d158b021e1baf359218fe4f499fcdbac195b672b8 +size 6132433824 diff --git a/GaMS-27B-Instruct-Nemotron.i1-IQ2_M.gguf b/GaMS-27B-Instruct-Nemotron.i1-IQ2_M.gguf new file mode 100644 index 0000000..fce27c5 --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91ba7fe5d3db25f933997d0a5d02982d0cf1560da75d64e599a744b6af269a16 +size 9398879136 diff --git a/GaMS-27B-Instruct-Nemotron.i1-IQ2_S.gguf b/GaMS-27B-Instruct-Nemotron.i1-IQ2_S.gguf new file mode 100644 index 0000000..7067315 --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f207b67422bd8ed435cc62f2dec994fb6f300807c3652523f4e4681c080ecc70 +size 8652161952 diff --git a/GaMS-27B-Instruct-Nemotron.i1-IQ2_XS.gguf b/GaMS-27B-Instruct-Nemotron.i1-IQ2_XS.gguf new file mode 100644 index 0000000..9c6257a --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07173f32a627a255f8b02688b1d27e15313d3a00dc0081cbb93f5317ca280a3e +size 8399717280 diff --git a/GaMS-27B-Instruct-Nemotron.i1-IQ2_XXS.gguf b/GaMS-27B-Instruct-Nemotron.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..479fb40 --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f65bb77e9245fa70c7bcd05591abbd53be273221cc461fd33fccf4d62b4280a +size 7625868192 diff --git a/GaMS-27B-Instruct-Nemotron.i1-IQ3_M.gguf b/GaMS-27B-Instruct-Nemotron.i1-IQ3_M.gguf new file mode 100644 index 0000000..ebb52a9 --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5af4096f6b728e73b053100123785427a6774b29f8a1b180ae03c3b6cb7e182 +size 12454831008 diff --git a/GaMS-27B-Instruct-Nemotron.i1-IQ3_S.gguf b/GaMS-27B-Instruct-Nemotron.i1-IQ3_S.gguf new file mode 100644 index 0000000..9c2335a --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9c530a7bd00155bd5db5ed24a34b3e5fce7702e9cab1708ea6febb26c73a215 +size 12169061280 diff --git a/GaMS-27B-Instruct-Nemotron.i1-IQ3_XS.gguf b/GaMS-27B-Instruct-Nemotron.i1-IQ3_XS.gguf new file mode 100644 index 0000000..2fdbbfd --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6621d5777fc9744c9368be1efa64ca776ac8e6eb6f837e82746b854e72aa2f6e +size 11550630816 diff --git a/GaMS-27B-Instruct-Nemotron.i1-IQ3_XXS.gguf b/GaMS-27B-Instruct-Nemotron.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..cc99c44 --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5e37411a6c904d05f5db94f7365504138d4ee66e7330ef44b0216b3b077e5b0 +size 10750755744 diff --git a/GaMS-27B-Instruct-Nemotron.i1-IQ4_XS.gguf b/GaMS-27B-Instruct-Nemotron.i1-IQ4_XS.gguf new file mode 100644 index 0000000..8edd9fc --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98e25c9acb20cfc8c557a852ad3d2c31d6224cec7bfcd9d7c0eb2ff761c1582f +size 14814421920 diff --git a/GaMS-27B-Instruct-Nemotron.i1-Q2_K.gguf b/GaMS-27B-Instruct-Nemotron.i1-Q2_K.gguf new file mode 100644 index 0000000..df072af --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92a594614e61f317a625ccd911da427037e1e74da9155c25d6c95cb952a0dbd0 +size 10449576864 diff --git a/GaMS-27B-Instruct-Nemotron.i1-Q2_K_S.gguf b/GaMS-27B-Instruct-Nemotron.i1-Q2_K_S.gguf new file mode 100644 index 0000000..0811bf3 --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:900306b3d484e7c8a1ee39f5e237cb44826606b4538ef0ddbe4c0b5017fa306c +size 9722766240 diff --git a/GaMS-27B-Instruct-Nemotron.i1-Q3_K_L.gguf b/GaMS-27B-Instruct-Nemotron.i1-Q3_K_L.gguf new file mode 100644 index 0000000..337b343 --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:803c0904a70a6303dc6460c0fd07901b4ce347f7df4b8f5b4cf09acc7209344f +size 14519362464 diff --git a/GaMS-27B-Instruct-Nemotron.i1-Q3_K_M.gguf b/GaMS-27B-Instruct-Nemotron.i1-Q3_K_M.gguf new file mode 100644 index 0000000..01c736b --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f881666ecf68ca9d885598455f22155ee4d2310f90501a57e50180dd326bd3a9 +size 13424649120 diff --git a/GaMS-27B-Instruct-Nemotron.i1-Q3_K_S.gguf b/GaMS-27B-Instruct-Nemotron.i1-Q3_K_S.gguf new file mode 100644 index 0000000..a6d1ae6 --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b56ebd1fa253156fc5be6c874d8355725573034e9dd6c6f34a8b893fe4ed604 +size 12169061280 diff --git a/GaMS-27B-Instruct-Nemotron.i1-Q4_0.gguf b/GaMS-27B-Instruct-Nemotron.i1-Q4_0.gguf new file mode 100644 index 0000000..fce99b2 --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4811864890485d8bcf62076aa02dc01a9f50cff39edcd84ae25303b61a7ad5e +size 15681463200 diff --git a/GaMS-27B-Instruct-Nemotron.i1-Q4_1.gguf b/GaMS-27B-Instruct-Nemotron.i1-Q4_1.gguf new file mode 100644 index 0000000..43ed16b --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9f951ecaff721dd0d278e74c0883b66a037eb389be5452fc9d24193ba30683c +size 17256293280 diff --git a/GaMS-27B-Instruct-Nemotron.i1-Q4_K_M.gguf b/GaMS-27B-Instruct-Nemotron.i1-Q4_K_M.gguf new file mode 100644 index 0000000..229595a --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fd698cbc66adeb50a0ad0706458eea602193b46a0673fdd44a29ffb2c31b454 +size 16645383072 diff --git a/GaMS-27B-Instruct-Nemotron.i1-Q4_K_S.gguf b/GaMS-27B-Instruct-Nemotron.i1-Q4_K_S.gguf new file mode 100644 index 0000000..7a5b437 --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67b4fd4022bf78d3ec26c56f32649f478accc11b49f6d03b6a3638b665132517 +size 15739265952 diff --git a/GaMS-27B-Instruct-Nemotron.i1-Q5_K_M.gguf b/GaMS-27B-Instruct-Nemotron.i1-Q5_K_M.gguf new file mode 100644 index 0000000..bd35fb1 --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:572876a2d576c3d4ba400c7f09c0977513f58054172121d4163705acca8a5391 +size 19408118688 diff --git a/GaMS-27B-Instruct-Nemotron.i1-Q5_K_S.gguf b/GaMS-27B-Instruct-Nemotron.i1-Q5_K_S.gguf new file mode 100644 index 0000000..6192dbc --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3d11431b669e0e286ba6ef5347eb1e737f001c037d495221509aa79b06e7eb1 +size 18884207520 diff --git a/GaMS-27B-Instruct-Nemotron.i1-Q6_K.gguf b/GaMS-27B-Instruct-Nemotron.i1-Q6_K.gguf new file mode 100644 index 0000000..27d5a80 --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41716e8e6290d881bb15fa3742365ecdd281dd52b2351b4e6d8406859b689551 +size 22343525280 diff --git a/GaMS-27B-Instruct-Nemotron.imatrix.gguf b/GaMS-27B-Instruct-Nemotron.imatrix.gguf new file mode 100644 index 0000000..ebf3653 --- /dev/null +++ b/GaMS-27B-Instruct-Nemotron.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06e67a287ee432cdbc6cb6eea938a55b4e2f2d044062c4c1a57bdadcf41ce0cf +size 11825536 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3f1d425 --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ +--- +base_model: cjvt/GaMS-27B-Instruct-Nemotron +datasets: +- nvidia/Nemotron-Post-Training-Dataset-v1 +- cjvt/GaMS-Nemotron-Chat +language: +- sl +- en +library_name: transformers +license: gemma +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/cjvt/GaMS-27B-Instruct-Nemotron + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GaMS-27B-Instruct-Nemotron-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-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/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-IQ1_S.gguf) | i1-IQ1_S | 6.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-IQ1_M.gguf) | i1-IQ1_M | 6.8 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 7.7 | | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-IQ2_XS.gguf) | i1-IQ2_XS | 8.5 | | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-IQ2_S.gguf) | i1-IQ2_S | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-IQ2_M.gguf) | i1-IQ2_M | 9.5 | | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-Q2_K_S.gguf) | i1-Q2_K_S | 9.8 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-Q2_K.gguf) | i1-Q2_K | 10.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 10.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-IQ3_XS.gguf) | i1-IQ3_XS | 11.7 | | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-IQ3_S.gguf) | i1-IQ3_S | 12.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-Q3_K_S.gguf) | i1-Q3_K_S | 12.3 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-IQ3_M.gguf) | i1-IQ3_M | 12.6 | | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.5 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-Q3_K_L.gguf) | i1-Q3_K_L | 14.6 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-IQ4_XS.gguf) | i1-IQ4_XS | 14.9 | | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-Q4_0.gguf) | i1-Q4_0 | 15.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-Q4_K_S.gguf) | i1-Q4_K_S | 15.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-Q4_K_M.gguf) | i1-Q4_K_M | 16.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-Q4_1.gguf) | i1-Q4_1 | 17.4 | | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-Q5_K_S.gguf) | i1-Q5_K_S | 19.0 | | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-Q5_K_M.gguf) | i1-Q5_K_M | 19.5 | | +| [GGUF](https://huggingface.co/mradermacher/GaMS-27B-Instruct-Nemotron-i1-GGUF/resolve/main/GaMS-27B-Instruct-Nemotron.i1-Q6_K.gguf) | i1-Q6_K | 22.4 | 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. + +