commit 3fa0b4bb17ec9a18261beb44a4386ad5dc08122f Author: ModelHub XC Date: Wed Jul 8 17:58:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Cerebras-OPT-Fusion-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..528be72 --- /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 +Cerebras-OPT-Fusion.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-OPT-Fusion.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Cerebras-OPT-Fusion.i1-IQ1_M.gguf b/Cerebras-OPT-Fusion.i1-IQ1_M.gguf new file mode 100644 index 0000000..1c6d7e9 --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:545bb31622ba47091f9d5cb441964b75e0196acf054a528c17cdcbe3fa978632 +size 1710880032 diff --git a/Cerebras-OPT-Fusion.i1-IQ1_S.gguf b/Cerebras-OPT-Fusion.i1-IQ1_S.gguf new file mode 100644 index 0000000..08aa930 --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c739ddfe8485f71530e02b7e92918e5c66911b395bcc81c77c3ffd8805ec56ae +size 1578759456 diff --git a/Cerebras-OPT-Fusion.i1-IQ2_M.gguf b/Cerebras-OPT-Fusion.i1-IQ2_M.gguf new file mode 100644 index 0000000..b295624 --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6410c9c8badb1a44e0cda07c911f2579e5fe04e985d671c19e2927eeef4972a +size 2423847104 diff --git a/Cerebras-OPT-Fusion.i1-IQ2_S.gguf b/Cerebras-OPT-Fusion.i1-IQ2_S.gguf new file mode 100644 index 0000000..9d93f3c --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d70d89278d1a3d7411ddf48aee773e4c194155b363ab6a9a650d259ea186452 +size 2247686336 diff --git a/Cerebras-OPT-Fusion.i1-IQ2_XS.gguf b/Cerebras-OPT-Fusion.i1-IQ2_XS.gguf new file mode 100644 index 0000000..a5fa6fb --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf2500efe67de40c7bbb368a449f06cecca5d37ca603b81ce685725abbe5faec +size 2124018976 diff --git a/Cerebras-OPT-Fusion.i1-IQ2_XXS.gguf b/Cerebras-OPT-Fusion.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..d197657 --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f024060de754218a1e1629b7f3a1d5726ade5d2ea5d15043ff0f26ea4247e504 +size 1931080992 diff --git a/Cerebras-OPT-Fusion.i1-IQ3_M.gguf b/Cerebras-OPT-Fusion.i1-IQ3_M.gguf new file mode 100644 index 0000000..c392721 --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5c745379da521b724fdd8efcdc8f68e67f36d292294a3da60d03dd30752112e +size 3388613856 diff --git a/Cerebras-OPT-Fusion.i1-IQ3_S.gguf b/Cerebras-OPT-Fusion.i1-IQ3_S.gguf new file mode 100644 index 0000000..6029e39 --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:925057671519b268ec19d3b84bed0cc5aecb797f9137ea1ac672a9d256597cb1 +size 3067749600 diff --git a/Cerebras-OPT-Fusion.i1-IQ3_XS.gguf b/Cerebras-OPT-Fusion.i1-IQ3_XS.gguf new file mode 100644 index 0000000..dfd2d5b --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1959533aeee49d4b4f8873e20fbbd479793a11f895ab56ad955804dae7dc727a +size 2992252128 diff --git a/Cerebras-OPT-Fusion.i1-IQ3_XXS.gguf b/Cerebras-OPT-Fusion.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..456d7d7 --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79932d75565ce0401162fc56f0c9b2a8f73aed360e05f5b16c302af13b35249a +size 2763585728 diff --git a/Cerebras-OPT-Fusion.i1-IQ4_NL.gguf b/Cerebras-OPT-Fusion.i1-IQ4_NL.gguf new file mode 100644 index 0000000..293ef34 --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb08032c09053b5edec48e558d42a4f93eb7f65a500b0e76bcaa0ea42a3d7c3f +size 3950727424 diff --git a/Cerebras-OPT-Fusion.i1-IQ4_XS.gguf b/Cerebras-OPT-Fusion.i1-IQ4_XS.gguf new file mode 100644 index 0000000..c2dde33 --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfba718089cc17c1059a738b9236b39ff91b7c189e02aae5e72d933e26cd3ee1 +size 3742967936 diff --git a/Cerebras-OPT-Fusion.i1-Q2_K.gguf b/Cerebras-OPT-Fusion.i1-Q2_K.gguf new file mode 100644 index 0000000..d1b92ad --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:061a92f648208f442ac11ae3d6cadd2baec8a1cd5e1c33401f48b4752bd88c19 +size 2665161024 diff --git a/Cerebras-OPT-Fusion.i1-Q2_K_S.gguf b/Cerebras-OPT-Fusion.i1-Q2_K_S.gguf new file mode 100644 index 0000000..2bc2cab --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea429a5fb1256ea9f007a601b339dd01e9241124784b369e5a3d6a3f3c0316d2 +size 2455445824 diff --git a/Cerebras-OPT-Fusion.i1-Q3_K_L.gguf b/Cerebras-OPT-Fusion.i1-Q3_K_L.gguf new file mode 100644 index 0000000..e72ac4d --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a26a0852bc2408fcec05df4c5b2fa3a1eae95d0e89a1c74421bda972de45debc +size 3973719264 diff --git a/Cerebras-OPT-Fusion.i1-Q3_K_M.gguf b/Cerebras-OPT-Fusion.i1-Q3_K_M.gguf new file mode 100644 index 0000000..544c9d8 --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f1bfee8476f52366850a176073d89559fb8dc50d84e9560b0e9967121e14ad4 +size 3654952160 diff --git a/Cerebras-OPT-Fusion.i1-Q3_K_S.gguf b/Cerebras-OPT-Fusion.i1-Q3_K_S.gguf new file mode 100644 index 0000000..d556247 --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abdc3992b4a91c0dbea68d5c98adf9e408c1f8ec18d967a5c8bba8c0f6dffb3b +size 3067749600 diff --git a/Cerebras-OPT-Fusion.i1-Q4_0.gguf b/Cerebras-OPT-Fusion.i1-Q4_0.gguf new file mode 100644 index 0000000..4472775 --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc364679442b63a2895b79b7741626379972969d57d714eb0aaf7e2c544e36ea +size 3967504640 diff --git a/Cerebras-OPT-Fusion.i1-Q4_1.gguf b/Cerebras-OPT-Fusion.i1-Q4_1.gguf new file mode 100644 index 0000000..83a5ad8 --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76cec266d553c1b0171fc9524db83d2d109ced0dc36a380524380209203e9c4a +size 4366246400 diff --git a/Cerebras-OPT-Fusion.i1-Q4_K_M.gguf b/Cerebras-OPT-Fusion.i1-Q4_K_M.gguf new file mode 100644 index 0000000..6b52ab1 --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:818819013ea3e6f6c377023efa6489e4bf3bbdc608b57e5087a419d3c0d98963 +size 4428878080 diff --git a/Cerebras-OPT-Fusion.i1-Q4_K_S.gguf b/Cerebras-OPT-Fusion.i1-Q4_K_S.gguf new file mode 100644 index 0000000..22e7612 --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9a3cacd309d0bc1afba632bf80ce2ffd618e159e30abe7e6d609befec1d4977 +size 3984281856 diff --git a/Cerebras-OPT-Fusion.i1-Q5_K_M.gguf b/Cerebras-OPT-Fusion.i1-Q5_K_M.gguf new file mode 100644 index 0000000..6285c17 --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:298dd26f9b1c0238ba38f3392d53017c1687ee7d462f9c3a878e4c242d28cfaf +size 5138281216 diff --git a/Cerebras-OPT-Fusion.i1-Q5_K_S.gguf b/Cerebras-OPT-Fusion.i1-Q5_K_S.gguf new file mode 100644 index 0000000..0e9203b --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65c5ccd48daa87f26a7543e8e1efeb6c313e47d50399aa761313a8809e57a739 +size 4781765376 diff --git a/Cerebras-OPT-Fusion.i1-Q6_K.gguf b/Cerebras-OPT-Fusion.i1-Q6_K.gguf new file mode 100644 index 0000000..430f6ca --- /dev/null +++ b/Cerebras-OPT-Fusion.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20e45bcdefd16dc3cd5b8b664caad1abf34142680d3d9e46e0300c0e2f290384 +size 5664743200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b90896f --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: MatteoKhan/Cerebras-OPT-Fusion +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +tags: +- mergekit +- merged-model +- cerebras +- opt +- language-model +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/MatteoKhan/Cerebras-OPT-Fusion + + +static quants are available at https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-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/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-IQ1_M.gguf) | i1-IQ1_M | 1.8 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-IQ2_S.gguf) | i1-IQ2_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-IQ2_M.gguf) | i1-IQ2_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-IQ3_S.gguf) | i1-IQ3_S | 3.2 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.2 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-IQ3_M.gguf) | i1-IQ3_M | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-IQ4_XS.gguf) | i1-IQ4_XS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.1 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-Q4_0.gguf) | i1-Q4_0 | 4.1 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.1 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.1 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-Q4_1.gguf) | i1-Q4_1 | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-Q5_K_S.gguf) | i1-Q5_K_S | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-OPT-Fusion-i1-GGUF/resolve/main/Cerebras-OPT-Fusion.i1-Q6_K.gguf) | i1-Q6_K | 5.8 | 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. + +