commit d332981c90661be18b5f9bae54ea899617b282fd Author: ModelHub XC Date: Thu Jun 4 20:33:21 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ab68e97 --- /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 +Arsenic-Shahrazad-12B-v4.4.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Arsenic-Shahrazad-12B-v4.4.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-IQ1_M.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-IQ1_M.gguf new file mode 100644 index 0000000..7b4dce8 --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c21f4fe7cacb5fe87e3c9d6921f88fe3ae9993b5c71288aa7adbb3efd0ca3282 +size 3221629824 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-IQ1_S.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-IQ1_S.gguf new file mode 100644 index 0000000..8b9ce3e --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f85c9aaa58d41b09471734c8eba71815c8cc403a3449d6eee05884578005419e +size 2999217024 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-IQ2_M.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-IQ2_M.gguf new file mode 100644 index 0000000..4321562 --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1ee86c612bf3b71ddb163a3cfa1be0ab0a8479434386efe61303203ffed3b35 +size 4435028864 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-IQ2_S.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-IQ2_S.gguf new file mode 100644 index 0000000..b146be2 --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9ad70d9959c6dbdb8a4d155e509096ac8bf0a603678656cb86279e59491aabb +size 4138478464 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-IQ2_XS.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-IQ2_XS.gguf new file mode 100644 index 0000000..425fcf7 --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06233e885fb4a5374f373f5bee840e761df55cd851d394ad9b4c5013fc4e04f7 +size 3915082624 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-IQ2_XXS.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..4662b90 --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf8e97f83cefa1c128fd1f3ed7fd417013bc6b2e8627ef30b144a098370bcd9e +size 3592317824 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-IQ3_M.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-IQ3_M.gguf new file mode 100644 index 0000000..b87ae70 --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f38e93c7b7726b22c593c3683bac459b949a72caf7543e845ea5ea1541da321 +size 5722237824 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-IQ3_S.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-IQ3_S.gguf new file mode 100644 index 0000000..9c4108f --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95b5fd345c5c7e127a4d05838a1db0b7c8202af34d28b7fe965c5ffc8018fb5b +size 5562084224 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-IQ3_XS.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-IQ3_XS.gguf new file mode 100644 index 0000000..f04255e --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2471ffd196a03bdcb0f5d1bf6213a4389e9610aca20d5a79576958de04a0262 +size 5306493824 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-IQ3_XXS.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..f2394a8 --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95158c5930f8f80cc0ffdb0fa5edfe8c8a91e50fa44c003c900e916b76608446 +size 4945390464 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-IQ4_NL.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-IQ4_NL.gguf new file mode 100644 index 0000000..5e651be --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e36dd9daab57f44644dcc948576d5b2d414f51bb7e84ee6ad0b1ebdfb0a69df2 +size 7097920384 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-IQ4_XS.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-IQ4_XS.gguf new file mode 100644 index 0000000..546e098 --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2d74ab34fc17d47a72f512a10ba16fdf5bda7dd19fe267a71f83e6ec6439ae3 +size 6742715264 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-Q2_K.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-Q2_K.gguf new file mode 100644 index 0000000..dc448dd --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ad8612369742a656d42884e2b8f436d5e788635d5ff3b3101a1db92b7e0c1e8 +size 4791053184 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-Q2_K_S.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-Q2_K_S.gguf new file mode 100644 index 0000000..b805d75 --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a7a9f32836a43f80f3c203b213c7dc000de95b057efe634bb24cd44cff3c9da +size 4493683584 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-Q3_K_L.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-Q3_K_L.gguf new file mode 100644 index 0000000..ed82cc1 --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51ccde66387904944237efef40953c891d615365cba86004555e3278d2d39cfc +size 6561508224 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-Q3_K_M.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-Q3_K_M.gguf new file mode 100644 index 0000000..a289b6a --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebf2e8dc109c359efa82953028e821b4728b70a10c78b64448cf5aaac071e858 +size 6083095424 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-Q3_K_S.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-Q3_K_S.gguf new file mode 100644 index 0000000..35e037c --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71d2c10f683f9064aa4582b2ac31bcb9377cadefd7c85c38d663a43daef64863 +size 5534231424 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-Q4_0.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-Q4_0.gguf new file mode 100644 index 0000000..1e4c28c --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c5e00f4755fe9d089c761bc50b682364eb800ceb0d3c361d557386374d923ea +size 7094643584 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-Q4_1.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-Q4_1.gguf new file mode 100644 index 0000000..4a25931 --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a7d5ae8f11cc192020279857c6b11701d775865c9935dab289749d534d63f3d +size 7795223424 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-Q4_K_M.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-Q4_K_M.gguf new file mode 100644 index 0000000..26459cd --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94be7fe9618329b3b471870fb1aa35e3fee3055d4e6410b251315fc20b4006a4 +size 7477209984 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-Q4_K_S.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-Q4_K_S.gguf new file mode 100644 index 0000000..5cb59bb --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb21de3633e0776f6e1a21a3639efcf09e9aabf5e19a30d81271077133389845 +size 7120202624 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-Q5_K_M.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-Q5_K_M.gguf new file mode 100644 index 0000000..6b97383 --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10dd9534547784f0b77750f602e0c81b076a016ea237d8d17a11857219c8267a +size 8727636864 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-Q5_K_S.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-Q5_K_S.gguf new file mode 100644 index 0000000..e7d80a9 --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4372e82bcbf47cf35db90af09a5bc57c1ab07cf5f3296d974f411b9a77e128cc +size 8518740864 diff --git a/Arsenic-Shahrazad-12B-v4.4.i1-Q6_K.gguf b/Arsenic-Shahrazad-12B-v4.4.i1-Q6_K.gguf new file mode 100644 index 0000000..5517c3a --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5ee9423d2499d321d6359582286c26e1656640f365a26a58c567df23650cac0 +size 10056215424 diff --git a/Arsenic-Shahrazad-12B-v4.4.imatrix.gguf b/Arsenic-Shahrazad-12B-v4.4.imatrix.gguf new file mode 100644 index 0000000..ce83397 --- /dev/null +++ b/Arsenic-Shahrazad-12B-v4.4.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89a9bf7236b8156240225c6a9d6847dd242b87320a0c86097a22b1822256990f +size 7088192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..380ea5c --- /dev/null +++ b/README.md @@ -0,0 +1,89 @@ +--- +base_model: Lambent/Arsenic-Shahrazad-12B-v4.4 +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +- not-for-all-audiences +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/Lambent/Arsenic-Shahrazad-12B-v4.4 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Arsenic-Shahrazad-12B-v4.4-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-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/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-IQ1_S.gguf) | i1-IQ1_S | 3.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-IQ2_S.gguf) | i1-IQ2_S | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-IQ2_M.gguf) | i1-IQ2_M | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-IQ3_S.gguf) | i1-IQ3_S | 5.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-Q4_0.gguf) | i1-Q4_0 | 7.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-IQ4_NL.gguf) | i1-IQ4_NL | 7.2 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-Q4_1.gguf) | i1-Q4_1 | 7.9 | | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.6 | | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/Arsenic-Shahrazad-12B-v4.4-i1-GGUF/resolve/main/Arsenic-Shahrazad-12B-v4.4.i1-Q6_K.gguf) | i1-Q6_K | 10.2 | 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. + +