commit de9370296c275d4f7e9288ceffc404ab47894279 Author: ModelHub XC Date: Sat Jul 11 14:12:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Piranha-12B-v1a-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c320ce9 --- /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 +Piranha-12B-v1a.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Piranha-12B-v1a.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Piranha-12B-v1a.i1-IQ1_M.gguf b/Piranha-12B-v1a.i1-IQ1_M.gguf new file mode 100644 index 0000000..18025fa --- /dev/null +++ b/Piranha-12B-v1a.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55a20fbae2d0233893fe1db61e80d3c9d650ced387b6f5786c1145483fdf8405 +size 3221629376 diff --git a/Piranha-12B-v1a.i1-IQ1_S.gguf b/Piranha-12B-v1a.i1-IQ1_S.gguf new file mode 100644 index 0000000..5fc1dd8 --- /dev/null +++ b/Piranha-12B-v1a.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c683ea979da0633df25c5db5487b92f0d96c9d3fd847e7a4d6a0b853d27ecae5 +size 2999216576 diff --git a/Piranha-12B-v1a.i1-IQ2_M.gguf b/Piranha-12B-v1a.i1-IQ2_M.gguf new file mode 100644 index 0000000..2b36c21 --- /dev/null +++ b/Piranha-12B-v1a.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89507cced6299f7d881539ac7e2ca48f1a6913212a8e9b54780e8c6da613f9f9 +size 4435028416 diff --git a/Piranha-12B-v1a.i1-IQ2_S.gguf b/Piranha-12B-v1a.i1-IQ2_S.gguf new file mode 100644 index 0000000..948aaf2 --- /dev/null +++ b/Piranha-12B-v1a.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db7f2d3bba05dbe5cb87dd7c8b160f06c7f6a7103efe2a0ce8c0ef487d3dfa02 +size 4138478016 diff --git a/Piranha-12B-v1a.i1-IQ2_XS.gguf b/Piranha-12B-v1a.i1-IQ2_XS.gguf new file mode 100644 index 0000000..334e105 --- /dev/null +++ b/Piranha-12B-v1a.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d68956e2ba62a12f5be7481119c3c06478c4a4d48e60759085315692c78fa6de +size 3915082176 diff --git a/Piranha-12B-v1a.i1-IQ2_XXS.gguf b/Piranha-12B-v1a.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..2423702 --- /dev/null +++ b/Piranha-12B-v1a.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1ea05ed3ffa9935479ab839b1277afe945f35dee1cf5f3503718c38255addb8 +size 3592317376 diff --git a/Piranha-12B-v1a.i1-IQ3_M.gguf b/Piranha-12B-v1a.i1-IQ3_M.gguf new file mode 100644 index 0000000..719e233 --- /dev/null +++ b/Piranha-12B-v1a.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f258c439cab1a4cc21f62a9e071d798a9d514183255b15098d84e196c77119a4 +size 5722237376 diff --git a/Piranha-12B-v1a.i1-IQ3_S.gguf b/Piranha-12B-v1a.i1-IQ3_S.gguf new file mode 100644 index 0000000..1045b85 --- /dev/null +++ b/Piranha-12B-v1a.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cce6d7b501f57f760395feda64ecfe728b828096010fa6c67763033ac41c6f52 +size 5562083776 diff --git a/Piranha-12B-v1a.i1-IQ3_XS.gguf b/Piranha-12B-v1a.i1-IQ3_XS.gguf new file mode 100644 index 0000000..3de2117 --- /dev/null +++ b/Piranha-12B-v1a.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cb77605f64e6049a1944fa5df6b43b9c44c1c5b47f56c33ff5a4b81c0f27020 +size 5306493376 diff --git a/Piranha-12B-v1a.i1-IQ3_XXS.gguf b/Piranha-12B-v1a.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..8bc110f --- /dev/null +++ b/Piranha-12B-v1a.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5e79af2638cba11812c5c14b96404f0751625c3a7316d046cd26a425f4da8b8 +size 4945390016 diff --git a/Piranha-12B-v1a.i1-IQ4_NL.gguf b/Piranha-12B-v1a.i1-IQ4_NL.gguf new file mode 100644 index 0000000..e70dd3a --- /dev/null +++ b/Piranha-12B-v1a.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92d736c57ab7ff033ec5c3f611fed3dc7c2f2f1b3c618631fce1d192e2078973 +size 7097919936 diff --git a/Piranha-12B-v1a.i1-IQ4_XS.gguf b/Piranha-12B-v1a.i1-IQ4_XS.gguf new file mode 100644 index 0000000..58c90f4 --- /dev/null +++ b/Piranha-12B-v1a.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67241279576c1e001178d4e641b8968b111ca80e260bc2115f0aab7e2c079313 +size 6742714816 diff --git a/Piranha-12B-v1a.i1-Q2_K.gguf b/Piranha-12B-v1a.i1-Q2_K.gguf new file mode 100644 index 0000000..1e313fb --- /dev/null +++ b/Piranha-12B-v1a.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:848aec40297bbdd33f53663362df9c2e38ef0a266da8ef5750d84b94345f07ae +size 4791052736 diff --git a/Piranha-12B-v1a.i1-Q2_K_S.gguf b/Piranha-12B-v1a.i1-Q2_K_S.gguf new file mode 100644 index 0000000..7d8fce8 --- /dev/null +++ b/Piranha-12B-v1a.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86c4d151ee0e5afbc8abac7221580fb3e2d8a6ffed1c2d13fcd85d87a16f1565 +size 4493683136 diff --git a/Piranha-12B-v1a.i1-Q3_K_L.gguf b/Piranha-12B-v1a.i1-Q3_K_L.gguf new file mode 100644 index 0000000..34b3917 --- /dev/null +++ b/Piranha-12B-v1a.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c18f84018c4e38fb23ba4ec247b7db603fbdcf971e8015002262b1112fd429f3 +size 6561507776 diff --git a/Piranha-12B-v1a.i1-Q3_K_M.gguf b/Piranha-12B-v1a.i1-Q3_K_M.gguf new file mode 100644 index 0000000..4114219 --- /dev/null +++ b/Piranha-12B-v1a.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1821e22e297fc421c4556d6a7099ce8842459467ad1de64c4becd2f61e9b3499 +size 6083094976 diff --git a/Piranha-12B-v1a.i1-Q3_K_S.gguf b/Piranha-12B-v1a.i1-Q3_K_S.gguf new file mode 100644 index 0000000..c65134e --- /dev/null +++ b/Piranha-12B-v1a.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adffa84d2a130a744f8f5de42bbdaf97e845e592fdead6b2ba19c4af46cc3329 +size 5534230976 diff --git a/Piranha-12B-v1a.i1-Q4_0.gguf b/Piranha-12B-v1a.i1-Q4_0.gguf new file mode 100644 index 0000000..b9c9200 --- /dev/null +++ b/Piranha-12B-v1a.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:757dd095ce751f833e5959b25fcc2d5e0e4c1ff3e4c1c51b12d7a78ee4c291d3 +size 7094643136 diff --git a/Piranha-12B-v1a.i1-Q4_1.gguf b/Piranha-12B-v1a.i1-Q4_1.gguf new file mode 100644 index 0000000..409f65e --- /dev/null +++ b/Piranha-12B-v1a.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:494580f251ec2d7ff789ac96a97e3458c6a19b5ce8adc6e2e009cfa575809bad +size 7795222976 diff --git a/Piranha-12B-v1a.i1-Q4_K_M.gguf b/Piranha-12B-v1a.i1-Q4_K_M.gguf new file mode 100644 index 0000000..913865b --- /dev/null +++ b/Piranha-12B-v1a.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f82c55675a6bf1faf9f865953366de2077d7085e9500e7f0f46f1db742b5258 +size 7477209536 diff --git a/Piranha-12B-v1a.i1-Q4_K_S.gguf b/Piranha-12B-v1a.i1-Q4_K_S.gguf new file mode 100644 index 0000000..00f2a64 --- /dev/null +++ b/Piranha-12B-v1a.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b544081177caa67a5e035381e0efd37be4a6e0be4a1093ce6257fe93bc6cc042 +size 7120202176 diff --git a/Piranha-12B-v1a.i1-Q5_K_M.gguf b/Piranha-12B-v1a.i1-Q5_K_M.gguf new file mode 100644 index 0000000..b2e17ef --- /dev/null +++ b/Piranha-12B-v1a.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b5a37d4d090809bd8c2c949700729bc439dcb3470d0e9390621e065c3cee8fb +size 8727636416 diff --git a/Piranha-12B-v1a.i1-Q5_K_S.gguf b/Piranha-12B-v1a.i1-Q5_K_S.gguf new file mode 100644 index 0000000..ec461ae --- /dev/null +++ b/Piranha-12B-v1a.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:570efe00503c2a2f251d061564e9ae3ccda9c691cfb011587446bd0373beab3b +size 8518740416 diff --git a/Piranha-12B-v1a.i1-Q6_K.gguf b/Piranha-12B-v1a.i1-Q6_K.gguf new file mode 100644 index 0000000..173474f --- /dev/null +++ b/Piranha-12B-v1a.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d5a581898e44ae5deaf90098c828f66a0fc6c004585987de0f706f2b0dd4e3e +size 10056214976 diff --git a/Piranha-12B-v1a.imatrix.gguf b/Piranha-12B-v1a.imatrix.gguf new file mode 100644 index 0000000..4367f6b --- /dev/null +++ b/Piranha-12B-v1a.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c18a48d6ac38857f8b9bdd52d53e5531e2a1bfd01899683069575239ad017a0d +size 7088192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9a3d220 --- /dev/null +++ b/README.md @@ -0,0 +1,90 @@ +--- +base_model: Naphula-Archives/Piranha-12B-v1a +language: eng +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +- mistral +- nemo +- karcher_stock +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/Naphula-Archives/Piranha-12B-v1a + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Piranha-12B-v1a-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Piranha-12B-v1a-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/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-IQ1_S.gguf) | i1-IQ1_S | 3.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-IQ2_S.gguf) | i1-IQ2_S | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-IQ2_M.gguf) | i1-IQ2_M | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-IQ3_S.gguf) | i1-IQ3_S | 5.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-Q4_0.gguf) | i1-Q4_0 | 7.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-IQ4_NL.gguf) | i1-IQ4_NL | 7.2 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-Q4_1.gguf) | i1-Q4_1 | 7.9 | | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.6 | | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/Piranha-12B-v1a-i1-GGUF/resolve/main/Piranha-12B-v1a.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. + +