commit 20f1cb41b4db4681067cc3678a9d7f7d3e14caf7 Author: ModelHub XC Date: Tue May 19 17:19:42 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..032cd5b --- /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 +Dolphin-Mistral-24B-Venice-fp16.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-Mistral-24B-Venice-fp16.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-IQ1_M.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-IQ1_M.gguf new file mode 100644 index 0000000..4fe9724 --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50c7a8e1a8a4ebec7e2e4fb577f47a36f9271d02503019ca7f6715ae2483c5a2 +size 5750496096 diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-IQ1_S.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-IQ1_S.gguf new file mode 100644 index 0000000..9ae55e7 --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e05919cdad44cd85a3833c9495d5873e312b7afb6d7dcd2c32d9b9236f95502d +size 5273721696 diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-IQ2_M.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-IQ2_M.gguf new file mode 100644 index 0000000..2dd67dc --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d4e0ec2e22d5029a2dbc6a22d8ab2c1fcaef96b28a21ad3d8abbb297d91af4f +size 8114051936 diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-IQ2_S.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-IQ2_S.gguf new file mode 100644 index 0000000..451ba67 --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dbee3e20cab0a975e9f0e1ff070bd4999a709eb165061b92242d77f4c3ecd7c +size 7478352736 diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-IQ2_XS.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-IQ2_XS.gguf new file mode 100644 index 0000000..036c575 --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0cffbb2c55d3c7c25dd182f469754c2437be578a93ef38d76f8d0b1f6283f7f +size 7207033696 diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-IQ2_XXS.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..ed2c3dd --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:465b5dea3b1c9814c3c5f118191d152656651f0af4d1697f46487c16f28bf6a4 +size 6545120096 diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-IQ3_M.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-IQ3_M.gguf new file mode 100644 index 0000000..eb29037 --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:038c82fb6b7a4cab4360b47bfed1480a3af3c70555710d6702e2ca9f1452918f +size 10650950496 diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-IQ3_S.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-IQ3_S.gguf new file mode 100644 index 0000000..3c5d65c --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80b97bad235b3ce188881b8dc77b425d293d55fed114e3de84505d7445f0cd98 +size 10428128096 diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-IQ3_XS.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-IQ3_XS.gguf new file mode 100644 index 0000000..5531964 --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f60d8ac4880a8d2f4696816363418c431066ba3173582635c39d9fa843e19e8 +size 9907116896 diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-IQ3_XXS.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..025295e --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6823770e24c53e04f9887e557470442209a427a6c62c6a4f0cbe52ca2f02021f +size 9280592736 diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-IQ4_XS.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-IQ4_XS.gguf new file mode 100644 index 0000000..0bc1c63 --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48a9eda79356bd34558d2fc44720ae5980368ef87fbc58d1aaf66aceb1dce778 +size 12758915936 diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-Q2_K.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-Q2_K.gguf new file mode 100644 index 0000000..0445d6b --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d86fd1f56955d4681e42ec65f264ecfc935a478f52f2f9d189ef3a76a082889d +size 8890325856 diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-Q2_K_S.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-Q2_K_S.gguf new file mode 100644 index 0000000..84db262 --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb32f69f7df765fad9624bb99f17f28e13324236b69d04e256eb0cdb29001751 +size 8320162656 diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-Q3_K_L.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-Q3_K_L.gguf new file mode 100644 index 0000000..0ab940e --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea378c150304286c020396c40b14c61afaef924ebe6974dfa90f537f3de25310 +size 12400761696 diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-Q3_K_M.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-Q3_K_M.gguf new file mode 100644 index 0000000..af36edc --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cce91c1f52206f9520508e326059eccc02d89a580d0dbde68589a66a97e65b95 +size 11474082656 diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-Q3_K_S.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-Q3_K_S.gguf new file mode 100644 index 0000000..20da269 --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c48a17cb5e6bdd0db1e36ed4aaf73a96e87fa35c8f95d3415bd697eba1c44989 +size 10400275296 diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-Q4_0.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-Q4_0.gguf new file mode 100644 index 0000000..980558a --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aad70d95c5fd874a4e3ea90c4a23f573ffb4f0c9fefac4f826e53a248391a90 +size 13494229856 diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-Q4_1.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-Q4_1.gguf new file mode 100644 index 0000000..62a7bf8 --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:482d3c65d76735c6bba0702f99603b170ad3ce3e2a04a4e7e3908480ace7c016 +size 14873107296 diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-Q4_K_M.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-Q4_K_M.gguf new file mode 100644 index 0000000..f70de3f --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78ac72414357d751f50050b7169fe18cb945d6d27ddd02ef877a43ea8c4f02ab +size 14333909856 diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-Q4_K_S.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-Q4_K_S.gguf new file mode 100644 index 0000000..0044de5 --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0313d4b31ee1f1b1c6369b5431816e2b0db084b2be693b4a42df82a115348260 +size 13549280096 diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-Q5_K_M.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-Q5_K_M.gguf new file mode 100644 index 0000000..c72dc8d --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85b179f4e57fa9badbad3fa153c5eceff6dc9b77a92b81bcf0a42be2fcb9b00d +size 16763984736 diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-Q5_K_S.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-Q5_K_S.gguf new file mode 100644 index 0000000..740f38e --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daeae08bb1f8046dbce6df4a93108f96ad0629a01ed3208b9a6557520825c512 +size 16304413536 diff --git a/Dolphin-Mistral-24B-Venice-fp16.i1-Q6_K.gguf b/Dolphin-Mistral-24B-Venice-fp16.i1-Q6_K.gguf new file mode 100644 index 0000000..dec54e8 --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39e8f3ab54e8c1d576448670decdf4b575bcbe9231d348c18d738bb33e017773 +size 19345939296 diff --git a/Dolphin-Mistral-24B-Venice-fp16.imatrix.gguf b/Dolphin-Mistral-24B-Venice-fp16.imatrix.gguf new file mode 100644 index 0000000..19da31b --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-fp16.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b47efd56ee20e26ec56200635fdce7bc892feaefa85bb1a7152fe0b0a44433f +size 10037312 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e1b1edf --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: root4k/Dolphin-Mistral-24B-Venice-fp16 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mlx +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/root4k/Dolphin-Mistral-24B-Venice-fp16 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Dolphin-Mistral-24B-Venice-fp16-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-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/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-IQ1_S.gguf) | i1-IQ1_S | 5.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-IQ1_M.gguf) | i1-IQ1_M | 5.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-IQ2_XS.gguf) | i1-IQ2_XS | 7.3 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-IQ2_S.gguf) | i1-IQ2_S | 7.6 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-IQ2_M.gguf) | i1-IQ2_M | 8.2 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-Q2_K_S.gguf) | i1-Q2_K_S | 8.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-Q2_K.gguf) | i1-Q2_K | 9.0 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 9.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-IQ3_XS.gguf) | i1-IQ3_XS | 10.0 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-Q3_K_S.gguf) | i1-Q3_K_S | 10.5 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-IQ3_S.gguf) | i1-IQ3_S | 10.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-IQ3_M.gguf) | i1-IQ3_M | 10.8 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-Q3_K_M.gguf) | i1-Q3_K_M | 11.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-Q3_K_L.gguf) | i1-Q3_K_L | 12.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.9 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-Q4_0.gguf) | i1-Q4_0 | 13.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-Q4_K_S.gguf) | i1-Q4_K_S | 13.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-Q4_K_M.gguf) | i1-Q4_K_M | 14.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-Q4_1.gguf) | i1-Q4_1 | 15.0 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-Q5_K_S.gguf) | i1-Q5_K_S | 16.4 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-Q5_K_M.gguf) | i1-Q5_K_M | 16.9 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-Mistral-24B-Venice-fp16-i1-GGUF/resolve/main/Dolphin-Mistral-24B-Venice-fp16.i1-Q6_K.gguf) | i1-Q6_K | 19.4 | 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. + +