commit 7df2751a60b7bdb5549e37e13a2c3282b4bf3d35 Author: ModelHub XC Date: Tue Apr 21 21:41:39 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d06c0d2 --- /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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-IQ1_M.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-IQ1_M.gguf new file mode 100644 index 0000000..3be12c4 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da1163c27a5c23f1f7953f0f47b5359f0d16d2774d408abceef6fd5e474d7efa +size 924188224 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-IQ1_S.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-IQ1_S.gguf new file mode 100644 index 0000000..7852e48 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eea51a793924dc3a9a09a1cefd5232f4d50482377377c9c247370e767431dbfe +size 868154944 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-IQ2_M.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-IQ2_M.gguf new file mode 100644 index 0000000..6f623fc --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef2f9ca64e90711ae99727afd29d4ca22b9e15d8abb23d835c03d39e46da470d +size 1229028928 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-IQ2_S.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-IQ2_S.gguf new file mode 100644 index 0000000..5af8b02 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93612833fb181c9155d9d085703bb05f5d93d406678e1ef02ab0c67b2698bbd8 +size 1154317888 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-IQ2_XS.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-IQ2_XS.gguf new file mode 100644 index 0000000..d5bfa3f --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9332d5fe6bd106864b9ee1605d74264db9884018158d114a92a80120d8205c7a +size 1100545600 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-IQ2_XXS.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..5670150 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21b85eed71b6d1d551dda2c6fe6305e39cce51bc752c8445b2086a1ab77195ea +size 1017577024 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-IQ3_M.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-IQ3_M.gguf new file mode 100644 index 0000000..374de09 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bcc8ef76d018ea8cc5982ca2220be1eb4c8808d0d501e8423bc3249a206415c +size 1599665728 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-IQ3_S.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-IQ3_S.gguf new file mode 100644 index 0000000..e9b1009 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a86f9a785367893397ef9fd30373f913ad424a92a24a7cfbc582ef454cbd3da +size 1542846016 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-IQ3_XS.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-IQ3_XS.gguf new file mode 100644 index 0000000..817ce31 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b34751c46d54647d43a94560dbf9f1010d9ae86763577c5d57e5c6076ce3439 +size 1476785728 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-IQ3_XXS.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..0636fe4 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dceb8509c4415cad42c24a854d63987b04d423d0568304ca430dcb8c35abc94 +size 1348763200 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-IQ4_NL.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-IQ4_NL.gguf new file mode 100644 index 0000000..c2684cb --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d2a17a877033db8f412bd99bd07c8f644e19d2e959bb97068e39a06b8566ed4 +size 1917187648 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-IQ4_XS.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-IQ4_XS.gguf new file mode 100644 index 0000000..70c2fa5 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e19cd14fb162c64bbc010b01c842e448e53603c386daed52d70134bf83f3222 +size 1829107264 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-Q2_K.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-Q2_K.gguf new file mode 100644 index 0000000..46f3182 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c5a44610d0b0395824d62328b96111a421bdeee53dc89b614e67bd917d16078 +size 1363932736 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-Q2_K_S.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-Q2_K_S.gguf new file mode 100644 index 0000000..7c32888 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59a5948359f5c2a63d644cb2e9b50955cf99d536933010f5ab94b284c73ca860 +size 1274279488 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-Q3_K_L.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-Q3_K_L.gguf new file mode 100644 index 0000000..a4ca0f4 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea59dbc5319b6e0a54a30b9bb95bfb33ce781a56a3c097ade9c324fc0227e1f0 +size 1815344704 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-Q3_K_M.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-Q3_K_M.gguf new file mode 100644 index 0000000..2eb08ad --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13d6dd12f3aaebd06e52752ecde49afed913bb77d31b1276f1a32bf376e2a35b +size 1687156288 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-Q3_K_S.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-Q3_K_S.gguf new file mode 100644 index 0000000..56743d3 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c287fc0c1bdd72ee447b4e4a45d72edf3c5c5f4e0c705e839dbd5a9ef285b57 +size 1542846016 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-Q4_0.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-Q4_0.gguf new file mode 100644 index 0000000..0757d03 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abbc6fd19f2985241a17fe790fbb3e83f839b86ac195c98eb98d13b9cb5d2301 +size 1921906240 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-Q4_1.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-Q4_1.gguf new file mode 100644 index 0000000..7cc4438 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11810dfb766c3b3f2d653c202d3586b10a399c297a9930dde9ba0e9cb46e57d1 +size 2093348416 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-Q4_K_M.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-Q4_K_M.gguf new file mode 100644 index 0000000..51e1349 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bc489925e8aaccd1ffc6834a0367ef1388a458aeb498a6332ab052ca55f616c +size 2019374656 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-Q4_K_S.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-Q4_K_S.gguf new file mode 100644 index 0000000..8bd14d7 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aefd85a3c77dfb93731ee0adacc25235ca3f903b3e9983772de50fafcfda43e +size 1928197696 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-Q5_K_M.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-Q5_K_M.gguf new file mode 100644 index 0000000..94b94d3 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5574290627e3261a606812a00cacc675e7f70e490e6e1402e9e642a74d05116 +size 2322150976 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-Q5_K_S.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-Q5_K_S.gguf new file mode 100644 index 0000000..e2a6210 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a701243e81d7462cc1d9930629b551033a0e23606c4fb021c13a5fff7ed08725 +size 2269509184 diff --git a/FuseChat-Llama-3.2-3B-SFT.i1-Q6_K.gguf b/FuseChat-Llama-3.2-3B-SFT.i1-Q6_K.gguf new file mode 100644 index 0000000..1c5d2d0 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59268487c779c14f7af17616aa253e23cdb836af57743d86fcc777ae05f01218 +size 2643850816 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bee54dd --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: FuseAI/FuseChat-Llama-3.2-3B-SFT +datasets: +- FuseAI/FuseChat-3.0-SFT-Data +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/FuseAI/FuseChat-Llama-3.2-3B-SFT + + +static quants are available at https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-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/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-Q4_1.gguf) | i1-Q4_1 | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.i1-Q6_K.gguf) | i1-Q6_K | 2.7 | 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..3177016 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97223439c7f7035e3ce094ee871704b85aa0c108f96baec13b82a2a9b820dec7 +size 2988377