commit de51ec3832855bf3490bfc35f1d592e975dee6f7 Author: ModelHub XC Date: Tue May 19 07:17:57 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/L3.1-Blackholev2-12B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f3d6577 --- /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 +L3.1-Blackholev2-12B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Blackholev2-12B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/L3.1-Blackholev2-12B.i1-IQ1_M.gguf b/L3.1-Blackholev2-12B.i1-IQ1_M.gguf new file mode 100644 index 0000000..6c8cd7b --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2930e1c105b487d6a4cec80b600491ca5acce024209b8bc999ed81caeb56cb40 +size 3072084512 diff --git a/L3.1-Blackholev2-12B.i1-IQ1_S.gguf b/L3.1-Blackholev2-12B.i1-IQ1_S.gguf new file mode 100644 index 0000000..d56d6a8 --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88ba84693cfd6cf437f1061dea1557f005fa8d5959dcfcac4fe2cc867c904ad6 +size 2849327648 diff --git a/L3.1-Blackholev2-12B.i1-IQ2_M.gguf b/L3.1-Blackholev2-12B.i1-IQ2_M.gguf new file mode 100644 index 0000000..7314343 --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f4605337e9c29c6a7adfa7591f6ff22f5c8ea4b92c141358b0b720af81a25f2 +size 4270693920 diff --git a/L3.1-Blackholev2-12B.i1-IQ2_S.gguf b/L3.1-Blackholev2-12B.i1-IQ2_S.gguf new file mode 100644 index 0000000..1b73f0f --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6f3c2589e6666458636b74d94fd9ab0ba00567822b99b0df27f58599169d9cc +size 3973684768 diff --git a/L3.1-Blackholev2-12B.i1-IQ2_XS.gguf b/L3.1-Blackholev2-12B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..2ae0b9c --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10049061b5f8a29f876c59e6535f08ac9e1c5a12b979e7b51ceceb58e918ffcf +size 3766569504 diff --git a/L3.1-Blackholev2-12B.i1-IQ2_XXS.gguf b/L3.1-Blackholev2-12B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..9815f9e --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1762504cfea66141985ce9f468994865ad6cc42d2f7055a51e50d45125204bfd +size 3443345952 diff --git a/L3.1-Blackholev2-12B.i1-IQ3_M.gguf b/L3.1-Blackholev2-12B.i1-IQ3_M.gguf new file mode 100644 index 0000000..8758bb0 --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4abc12a56437460bbec4ee2507cc619345167a9ce82eaeccffab0ec51b27421a +size 5538218528 diff --git a/L3.1-Blackholev2-12B.i1-IQ3_S.gguf b/L3.1-Blackholev2-12B.i1-IQ3_S.gguf new file mode 100644 index 0000000..d255cae --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81bad68792ae37eb04791be8e7926b5c72ffbcde202a68ae1cd15b2ee0e0d182 +size 5380014624 diff --git a/L3.1-Blackholev2-12B.i1-IQ3_XS.gguf b/L3.1-Blackholev2-12B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..31d87f9 --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7d446f6cae8780d740076d58da3360f4c8749e47eb78ea70477db447064351c +size 5127176736 diff --git a/L3.1-Blackholev2-12B.i1-IQ3_XXS.gguf b/L3.1-Blackholev2-12B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..e693e15 --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45b185004f89eda7f8f4b0a0eed72aea2a2efa3bc3aa4ed06953f0f6173f302a +size 4782661152 diff --git a/L3.1-Blackholev2-12B.i1-IQ4_NL.gguf b/L3.1-Blackholev2-12B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..c1c0a11 --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb9c68fcdd7b5d7bea3b69414e5029af9191e53637b5472b50644f6f16ba44d1 +size 6896510496 diff --git a/L3.1-Blackholev2-12B.i1-IQ4_XS.gguf b/L3.1-Blackholev2-12B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..cf02e86 --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5d9215affafaee06348db6dacbb4fca25ff0cc6bc7c4e7f0ea19f5a723a0ee6 +size 6545856032 diff --git a/L3.1-Blackholev2-12B.i1-Q2_K.gguf b/L3.1-Blackholev2-12B.i1-Q2_K.gguf new file mode 100644 index 0000000..5521cb8 --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4ca3fb16adeca9fbb62209941578f9909f9ce18b8286477f2b7a6ca59b55683 +size 4623773216 diff --git a/L3.1-Blackholev2-12B.i1-Q2_K_S.gguf b/L3.1-Blackholev2-12B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..60aaff6 --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:360d69289b1067ee8c5c27863c38c081f4cb88b6601df968de459573e47fc324 +size 4322962976 diff --git a/L3.1-Blackholev2-12B.i1-Q3_K_L.gguf b/L3.1-Blackholev2-12B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..aec6d3a --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9fbaece05515af233661c6308452ad82416fc0da5f72c8d7507770faed66498 +size 6379438624 diff --git a/L3.1-Blackholev2-12B.i1-Q3_K_M.gguf b/L3.1-Blackholev2-12B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..fe23d1f --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e10db7277cf3957d90a2eb26bdecbc6fd0677c923f9d91d880e1de85328151b1 +size 5904433696 diff --git a/L3.1-Blackholev2-12B.i1-Q3_K_S.gguf b/L3.1-Blackholev2-12B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..08abe26 --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4053d6425d2ca204feb85750e1782289522eb8e3143c39fad6255315c1619844 +size 5352161824 diff --git a/L3.1-Blackholev2-12B.i1-Q4_0.gguf b/L3.1-Blackholev2-12B.i1-Q4_0.gguf new file mode 100644 index 0000000..8422e80 --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb74dc8c9d1921cbd201d5639df9d1ab559c76ed7bb73b3e56f2bb0430606b52 +size 6892316192 diff --git a/L3.1-Blackholev2-12B.i1-Q4_1.gguf b/L3.1-Blackholev2-12B.i1-Q4_1.gguf new file mode 100644 index 0000000..5982e6e --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18cad1e3c93b9bd063da37b10071b4625b5b70bf6331ae2dc447dbc8011a80bc +size 7584712224 diff --git a/L3.1-Blackholev2-12B.i1-Q4_K_M.gguf b/L3.1-Blackholev2-12B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..b33083a --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f650eac0959eec8a37093cca1b27758285f789de367069082732ace076279c1 +size 7275800096 diff --git a/L3.1-Blackholev2-12B.i1-Q4_K_S.gguf b/L3.1-Blackholev2-12B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..e84874d --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62eb46cb273b7ce4591e4460ca8228ea2ca99bb55aafd32da8493160edf7f1d9 +size 6916433440 diff --git a/L3.1-Blackholev2-12B.i1-Q5_K_M.gguf b/L3.1-Blackholev2-12B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..2d27c86 --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:409e7d673fe095694063ecccfa267d4f495fbb70838aae02a319d653c9dd052b +size 8508024352 diff --git a/L3.1-Blackholev2-12B.i1-Q5_K_S.gguf b/L3.1-Blackholev2-12B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..5310007 --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ec2132ad7e4548f153dfefa4a2d2d776c3c916f027397e8cd59584bb9454e1a +size 8299128352 diff --git a/L3.1-Blackholev2-12B.i1-Q6_K.gguf b/L3.1-Blackholev2-12B.i1-Q6_K.gguf new file mode 100644 index 0000000..9085c9b --- /dev/null +++ b/L3.1-Blackholev2-12B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83b5d61c77d34964f35251d07a179f903304cc8a550f514e664155163334f4b9 +size 9817262624 diff --git a/L3.1-Blackholev2-12B.imatrix.gguf b/L3.1-Blackholev2-12B.imatrix.gguf new file mode 100644 index 0000000..d062278 --- /dev/null +++ b/L3.1-Blackholev2-12B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e112cd01a065de87b989352060c12c6ceddc29ac6da8443a17bb01f98b6a642 +size 7836224 diff --git a/README.md b/README.md new file mode 100644 index 0000000..11bea5c --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: kromcomp/L3.1-Blackholev2-12B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/kromcomp/L3.1-Blackholev2-12B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#L3.1-Blackholev2-12B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-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/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.9 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-IQ1_M.gguf) | i1-IQ1_M | 3.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-IQ2_S.gguf) | i1-IQ2_S | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-IQ2_M.gguf) | i1-IQ2_M | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-Q2_K.gguf) | i1-Q2_K | 4.7 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.5 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-IQ3_S.gguf) | i1-IQ3_S | 5.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-IQ3_M.gguf) | i1-IQ3_M | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-Q4_0.gguf) | i1-Q4_0 | 7.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 7.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-Q4_1.gguf) | i1-Q4_1 | 7.7 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.4 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.6 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Blackholev2-12B-i1-GGUF/resolve/main/L3.1-Blackholev2-12B.i1-Q6_K.gguf) | i1-Q6_K | 9.9 | 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. + +