commit fdb7e3d162d3198e427b801fe39cea5c05cfc283 Author: ModelHub XC Date: Sun Aug 9 11:19:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Kepler-8B-Instruct-v2-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..12765f4 --- /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 +Kepler-8B-Instruct-v2.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Kepler-8B-Instruct-v2.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Kepler-8B-Instruct-v2.i1-IQ1_M.gguf b/Kepler-8B-Instruct-v2.i1-IQ1_M.gguf new file mode 100644 index 0000000..780ea97 --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:373dc034b418ebd4871fc26e1c0ad1b05e0b37b254ba651766130637422378a0 +size 2040734080 diff --git a/Kepler-8B-Instruct-v2.i1-IQ1_S.gguf b/Kepler-8B-Instruct-v2.i1-IQ1_S.gguf new file mode 100644 index 0000000..5575669 --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bf61d672fb93dd1e653c57e72e839a3478b6de787e9bb4fef1b3564c57408e8 +size 1902205312 diff --git a/Kepler-8B-Instruct-v2.i1-IQ2_M.gguf b/Kepler-8B-Instruct-v2.i1-IQ2_M.gguf new file mode 100644 index 0000000..0c33970 --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd7c3afc75d018aaadefcaf13fc89b358d239ea9dde383351db8ff46c0fc8aa7 +size 2778735168 diff --git a/Kepler-8B-Instruct-v2.i1-IQ2_S.gguf b/Kepler-8B-Instruct-v2.i1-IQ2_S.gguf new file mode 100644 index 0000000..965324a --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2416a2e217836c85aa1367b3d00c8c2dcee55a61143fad13fdbc629af2691623 +size 2594030144 diff --git a/Kepler-8B-Instruct-v2.i1-IQ2_XS.gguf b/Kepler-8B-Instruct-v2.i1-IQ2_XS.gguf new file mode 100644 index 0000000..69decf7 --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d517f3196e97a293775bbbfb937222805c52fe773a470675ea3d218936ea9d33 +size 2467559808 diff --git a/Kepler-8B-Instruct-v2.i1-IQ2_XXS.gguf b/Kepler-8B-Instruct-v2.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..0ad3dfe --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbe54a709dbadf9f78bee42a41c00a905b82128312408f876d617a858b95b63e +size 2271615360 diff --git a/Kepler-8B-Instruct-v2.i1-IQ3_M.gguf b/Kepler-8B-Instruct-v2.i1-IQ3_M.gguf new file mode 100644 index 0000000..4692f1d --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d451991a328b9e3b729dec5293c4944a0a09d9b2935fa494b383dbcda9bd7dd +size 3572214880 diff --git a/Kepler-8B-Instruct-v2.i1-IQ3_S.gguf b/Kepler-8B-Instruct-v2.i1-IQ3_S.gguf new file mode 100644 index 0000000..a9a1689 --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1d1e6b4d1ed165af5f2cb91d3ae44039b6d9f1f908d78d1855bd76720be33dd +size 3497395296 diff --git a/Kepler-8B-Instruct-v2.i1-IQ3_XS.gguf b/Kepler-8B-Instruct-v2.i1-IQ3_XS.gguf new file mode 100644 index 0000000..eb73139 --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3b3f8ca20a070036acd79a2f99fe97cc27a388fa91b0f3f0ce422ab17f1545f +size 3344458848 diff --git a/Kepler-8B-Instruct-v2.i1-IQ3_XXS.gguf b/Kepler-8B-Instruct-v2.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..47d33f6 --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a0bcdb51ac164a5fd25eeeed0ed6d2aac8115babf81c6a72b7286eca5f4a42d +size 3112907328 diff --git a/Kepler-8B-Instruct-v2.i1-IQ4_NL.gguf b/Kepler-8B-Instruct-v2.i1-IQ4_NL.gguf new file mode 100644 index 0000000..c7c51de --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:059730b27da34fa5a73b316859954730437318580f8f5d74d94624820fd10f84 +size 4435826272 diff --git a/Kepler-8B-Instruct-v2.i1-IQ4_XS.gguf b/Kepler-8B-Instruct-v2.i1-IQ4_XS.gguf new file mode 100644 index 0000000..8a7c8ea --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c6e12aa9e642fd77f38ebd4b01c0cfcf351cb6009a7f1f967cb22c4677c42e3 +size 4216530176 diff --git a/Kepler-8B-Instruct-v2.i1-Q2_K.gguf b/Kepler-8B-Instruct-v2.i1-Q2_K.gguf new file mode 100644 index 0000000..9b1862a --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9b548c27d4167ac3966974027b9cba9a3a1e13a427da208acee9179c45af328 +size 3014288288 diff --git a/Kepler-8B-Instruct-v2.i1-Q2_K_S.gguf b/Kepler-8B-Instruct-v2.i1-Q2_K_S.gguf new file mode 100644 index 0000000..535c8f0 --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a5cb108ef4a9c1ea331a904d7a2c8ce103b156ecce6d8dde9005a72e572853b +size 2832421792 diff --git a/Kepler-8B-Instruct-v2.i1-Q3_K_L.gguf b/Kepler-8B-Instruct-v2.i1-Q3_K_L.gguf new file mode 100644 index 0000000..64809eb --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5431e634543a5f437435eb3418f28c5fc7ad61b404249edca3e7c29de2158f30 +size 4086662240 diff --git a/Kepler-8B-Instruct-v2.i1-Q3_K_M.gguf b/Kepler-8B-Instruct-v2.i1-Q3_K_M.gguf new file mode 100644 index 0000000..3677b80 --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3857f839fe238a6751c99dad169f74ac404bb484e8612836810800e316d9f201 +size 3806594144 diff --git a/Kepler-8B-Instruct-v2.i1-Q3_K_S.gguf b/Kepler-8B-Instruct-v2.i1-Q3_K_S.gguf new file mode 100644 index 0000000..aed8b70 --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0223ebeb08bf7e8606e17f34b0a01ce6c4b3470c9ac532577f365d8d7c903be +size 3490571360 diff --git a/Kepler-8B-Instruct-v2.i1-Q4_0.gguf b/Kepler-8B-Instruct-v2.i1-Q4_0.gguf new file mode 100644 index 0000000..5b1542f --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cde98c9db089356d74e0e74b33a26474e0ab7706964d1d5f1fac313768e61ac +size 4442134112 diff --git a/Kepler-8B-Instruct-v2.i1-Q4_1.gguf b/Kepler-8B-Instruct-v2.i1-Q4_1.gguf new file mode 100644 index 0000000..6058e00 --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bf90c37b6dbd69933815f4f9aab6d65ba382b35ef8aa58c3f3adcc13e92a2c6 +size 4871207232 diff --git a/Kepler-8B-Instruct-v2.i1-Q4_K_M.gguf b/Kepler-8B-Instruct-v2.i1-Q4_K_M.gguf new file mode 100644 index 0000000..9f50e4a --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ee88c9b6d91dabbfbc63f1f365e0c3dd9c5062797366325adbedcab881b47cd +size 4681086560 diff --git a/Kepler-8B-Instruct-v2.i1-Q4_K_S.gguf b/Kepler-8B-Instruct-v2.i1-Q4_K_S.gguf new file mode 100644 index 0000000..395ce7b --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d3da8d6bff84ff866456ff1e0e0007fd2d51f26ed08ae5ec9e13f9693a958ea +size 4455781984 diff --git a/Kepler-8B-Instruct-v2.i1-Q5_K_M.gguf b/Kepler-8B-Instruct-v2.i1-Q5_K_M.gguf new file mode 100644 index 0000000..ed2beb1 --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b5eb96779ad56f900376ec94ec2b7665a0e47f0d1b51a71bf5a5c719b5e2927 +size 5442665504 diff --git a/Kepler-8B-Instruct-v2.i1-Q5_K_S.gguf b/Kepler-8B-Instruct-v2.i1-Q5_K_S.gguf new file mode 100644 index 0000000..fbf70c2 --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:048143774a078981fe9ac09cb2eb7de7b509216b82fbfb17c9ee9206d7e9e9aa +size 5313010720 diff --git a/Kepler-8B-Instruct-v2.i1-Q6_K.gguf b/Kepler-8B-Instruct-v2.i1-Q6_K.gguf new file mode 100644 index 0000000..5e46447 --- /dev/null +++ b/Kepler-8B-Instruct-v2.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:970d01136820ee61a2bc7f0b34c4c6914dd62c8810ccb45ce9adc52898e9cbbf +size 6251843136 diff --git a/Kepler-8B-Instruct-v2.imatrix.gguf b/Kepler-8B-Instruct-v2.imatrix.gguf new file mode 100644 index 0000000..a1dc8e7 --- /dev/null +++ b/Kepler-8B-Instruct-v2.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:446681c913c89828e721b46dd4a6a59b03242f79d9c3efbf7eb419217da90594 +size 4560352 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3691c67 --- /dev/null +++ b/README.md @@ -0,0 +1,94 @@ +--- +base_model: intellectlabs/Kepler-8B-Instruct-v2 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- gguf +- llama.cpp +- quantized +- merge +- mergekit +- qwen2 +- text-generation +- conversational +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/intellectlabs/Kepler-8B-Instruct-v2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Kepler-8B-Instruct-v2-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-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/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.9 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-Q4_1.gguf) | i1-Q4_1 | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Kepler-8B-Instruct-v2-i1-GGUF/resolve/main/Kepler-8B-Instruct-v2.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | 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. + +