commit e2b3cadc366ad88f6fd34dcadf3a3a0fd7b96c89 Author: ModelHub XC Date: Mon Oct 19 08:10:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e14f79e --- /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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ1_M.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ1_M.gguf new file mode 100644 index 0000000..4a59f2f --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0774eafb3b57d78d0f9eac2c4a9454f5881e55daa599c8c8841d08f24954f85d +size 5750494464 diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ1_S.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ1_S.gguf new file mode 100644 index 0000000..6612579 --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61abfbd656d1bbd7f476f4f5539f4adb965d292238c2e19fed97c575e4243bf9 +size 5273720064 diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ2_M.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ2_M.gguf new file mode 100644 index 0000000..efdc660 --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50edfb68f01f6f2b456ab877e2600c69295e56aed8978ed55101772105d41560 +size 8114050304 diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ2_S.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ2_S.gguf new file mode 100644 index 0000000..a6f3633 --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26b2cae06b4a84ac24a885e5125403ae148fd0eb0f86f303d3bc3596dd015abb +size 7478351104 diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ2_XS.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ2_XS.gguf new file mode 100644 index 0000000..a8013f1 --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58ddc62d73757c62358aa3fbfc129007776b3e1db5da68116e8e4f4cd2c02149 +size 7207032064 diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ2_XXS.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..db91336 --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf5d581fffcbd9ec5c9d6695956e2e3f7ec0ba59ef0c0ce3ef7ae9dde0e1cf8a +size 6545118464 diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ3_M.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ3_M.gguf new file mode 100644 index 0000000..b05a3cb --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c5f0fee6c9b99e6ac962abc7fc18dffa237442c46f7ce5904c6a08982276ecb +size 10650948864 diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ3_S.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ3_S.gguf new file mode 100644 index 0000000..71b4777 --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:154fad9a68b9dac206c6f975dff8c86e206757131e87739aa8c5d1c3b1adc772 +size 10428126464 diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ3_XS.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ3_XS.gguf new file mode 100644 index 0000000..6fafdb3 --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca0e86c5f7341bc1f9402b651d93d71d28a278f2a791590a94f1b8dd8bba2254 +size 9907115264 diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ3_XXS.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..bb30476 --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe699a5471f66ea7f2fbe1759015fb5b470c940b5d9779d27835b3ce15b68b0a +size 9280591104 diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ4_XS.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ4_XS.gguf new file mode 100644 index 0000000..719a9e3 --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:588f557c077706c7324b5e047a2fad439f12b915d437f2468a75dd3968683470 +size 12758914304 diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q2_K.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q2_K.gguf new file mode 100644 index 0000000..8ccd53c --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41e774d2a078950cb27d969556417137f4cd2e1c8451b3c4eff141919845437e +size 8890324224 diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q2_K_S.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q2_K_S.gguf new file mode 100644 index 0000000..1f9f785 --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbfa1c52240581aeb3aada9ce75a7e3ff380faff4951f032e4612fbaf965d8e1 +size 8320161024 diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q3_K_L.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q3_K_L.gguf new file mode 100644 index 0000000..f677a46 --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af23e850d1fdf1694dc948144df478c0d0ab1af3332a2a7b8c995d2e3cbe4276 +size 12400760064 diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q3_K_M.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q3_K_M.gguf new file mode 100644 index 0000000..8207c9d --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b46af5e02d3668619a0d568aff4fded0a230ef33383192eb0860494d28631557 +size 11474081024 diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q3_K_S.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q3_K_S.gguf new file mode 100644 index 0000000..7e4f284 --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4808987e75133c82318c756a0ec3fbdb900449fe42a507419e263b8f760fe909 +size 10400273664 diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q4_0.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q4_0.gguf new file mode 100644 index 0000000..c8a9bd5 --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dc576078dc15b43fedc89543ad7ed5e062712ca7db0b49c97a929ff1e5d580c +size 13494228224 diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q4_1.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q4_1.gguf new file mode 100644 index 0000000..b8bb615 --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dbff32ea922147968fefb88e085d2cf6fc57cf5d375ba060b3b42e587d0c03f +size 14873105664 diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q4_K_M.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q4_K_M.gguf new file mode 100644 index 0000000..4d01327 --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be0b6fbac0a2643cd9ab86fab6fdb5fe35f59734197d5c3f5924c304b400b4a8 +size 14333908224 diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q4_K_S.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q4_K_S.gguf new file mode 100644 index 0000000..8c78ecc --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04136ed4f132218f86db497b385269a598952da98addeebf8303868b6ddddbb6 +size 13549278464 diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q5_K_M.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q5_K_M.gguf new file mode 100644 index 0000000..57e21ad --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84f7290df2af9736a9ca08bf383878486c2db7c70767a4254b5aad4bf83c66fa +size 16763983104 diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q5_K_S.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q5_K_S.gguf new file mode 100644 index 0000000..facc0b4 --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b215b12672c32bd17c3ba396e145c137d172097458b010d94e91fbc13ad2e013 +size 16304411904 diff --git a/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q6_K.gguf b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q6_K.gguf new file mode 100644 index 0000000..f85fad3 --- /dev/null +++ b/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74172f1790ddde4e1983b5a580e827c64ac32a0c43bf8e5c1912ff833c31f6b8 +size 19345937664 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f6d2337 --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: Dans-DiscountModels/Mistral-Small-3.1-24B-Base-2503-ChatML +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Dans-DiscountModels/Mistral-Small-3.1-24B-Base-2503-ChatML + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-GGUF + +**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-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/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ1_S.gguf) | i1-IQ1_S | 5.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ1_M.gguf) | i1-IQ1_M | 5.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ2_XS.gguf) | i1-IQ2_XS | 7.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ2_S.gguf) | i1-IQ2_S | 7.6 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ2_M.gguf) | i1-IQ2_M | 8.2 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q2_K_S.gguf) | i1-Q2_K_S | 8.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q2_K.gguf) | i1-Q2_K | 9.0 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 9.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ3_XS.gguf) | i1-IQ3_XS | 10.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q3_K_S.gguf) | i1-Q3_K_S | 10.5 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ3_S.gguf) | i1-IQ3_S | 10.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ3_M.gguf) | i1-IQ3_M | 10.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q3_K_M.gguf) | i1-Q3_K_M | 11.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q3_K_L.gguf) | i1-Q3_K_L | 12.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q4_0.gguf) | i1-Q4_0 | 13.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q4_K_S.gguf) | i1-Q4_K_S | 13.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q4_K_M.gguf) | i1-Q4_K_M | 14.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q4_1.gguf) | i1-Q4_1 | 15.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q5_K_S.gguf) | i1-Q5_K_S | 16.4 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.i1-Q5_K_M.gguf) | i1-Q5_K_M | 16.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-ChatML-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503-ChatML.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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..de57d2a --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:830ab9facc9093f5e2ab5d9ed70153d18b25bcb5340ca2421aa45ed1e0ebe289 +size 10003525