commit 2d46b8cd22c6c9b0a40dd924b4518c18b3d15eca Author: ModelHub XC Date: Fri Apr 24 04:31:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..614b39d --- /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 +LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ1_M.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ1_M.gguf new file mode 100644 index 0000000..d096a40 --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94d9e213d582feae66a711753340453b06ddebaa97d331a8c32d8968a309de63 +size 924192928 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ1_S.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ1_S.gguf new file mode 100644 index 0000000..c629f9d --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1765182eeb5dcae4f5196538d3cf2e271a72c4b8e3fc0a46e8440f4188a89b6d +size 868159648 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ2_M.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ2_M.gguf new file mode 100644 index 0000000..a33c1b9 --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c6578131c7cc77b746e484b54c0ea01d9bbdeb166cfbda2d4a754fca219862c +size 1229033632 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ2_S.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ2_S.gguf new file mode 100644 index 0000000..9d1136a --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17977b2e8627ab08a676fe7bacd5217ab47fc53e9bb71c5e605b22ef5810fa52 +size 1154322592 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ2_XS.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ2_XS.gguf new file mode 100644 index 0000000..ffd8894 --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ee453a9796740eb950b22378de530eb14fe3e053d1b2ed69f67d7d1c930aef2 +size 1100550304 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ2_XXS.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..eb5dec0 --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28086fed684c3b16b3eda1909b5f32cc2d8c52ccae0b1ee90a1b3a19ded0ed87 +size 1017581728 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ3_M.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ3_M.gguf new file mode 100644 index 0000000..700105d --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5b31293c9d58fca816917326dd4f13edba104a752135ebd8f740da18f996671 +size 1599670432 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ3_S.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ3_S.gguf new file mode 100644 index 0000000..8c034af --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca29fadcbbcb02b7df9fcbb2c683ce87b3c1b1261e55cb6bf4779c75de5e5dd7 +size 1542850720 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ3_XS.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ3_XS.gguf new file mode 100644 index 0000000..39a9c77 --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:060dd8af06ec5531efaefd5323773756c9b6caad7acea3b5f6ed751358b3acc8 +size 1476790432 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ3_XXS.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..a0942f4 --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ffcd2e45560ed4d81b789322717fc50f598fa32feeae7a95b0daa9321aaed8e +size 1348767904 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ4_NL.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ4_NL.gguf new file mode 100644 index 0000000..7fd0fa4 --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:878134eea1461b1a60127e42a8113849580538a4aa46c01cfe04900c8b955f59 +size 1917192352 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ4_XS.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ4_XS.gguf new file mode 100644 index 0000000..7ed8207 --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1b72355f08547a871c8af40c2addd466d8059c2e51390d0e935813a0b2c86ea +size 1829111968 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q2_K.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q2_K.gguf new file mode 100644 index 0000000..593ddb8 --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:197f32ec567a4272d04b0d135bf7527f128803b8aa013d2beb19c185c4c01265 +size 1363937440 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q2_K_S.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q2_K_S.gguf new file mode 100644 index 0000000..bd2796c --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb75923306cdab801d7d0bba5bc8e78cded37406885ba28902f06b89553bf1a6 +size 1274284192 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q3_K_L.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q3_K_L.gguf new file mode 100644 index 0000000..8e719ee --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fbba270dc269226d50a91e892aacfcb7a901cea8301340f5a5abd0fd95ee567 +size 1815349408 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q3_K_M.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q3_K_M.gguf new file mode 100644 index 0000000..54865f4 --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77d3176803fc4e4a0d89ba31eb015fcded83c833523c9714324e14f3d84f81de +size 1687160992 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q3_K_S.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q3_K_S.gguf new file mode 100644 index 0000000..d3c3e9b --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a15150a5ec76a8d747986a63b04e47e46cfec4b7107c9d10cd90fbacd6fc992 +size 1542850720 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q4_0.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q4_0.gguf new file mode 100644 index 0000000..004ef17 --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:791e4c70f9d9f5ef033f76bd19c7ae26b761c397a25f56059dc7683cfa5d1fc1 +size 1921910944 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q4_1.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q4_1.gguf new file mode 100644 index 0000000..4bbb435 --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:335493456f9acd0aafecfa71da7c7def6e29a92698e1edcbf04b4cc803f08de9 +size 2093353120 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q4_K_M.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q4_K_M.gguf new file mode 100644 index 0000000..90949a1 --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39290831e6948a3bf61c5a1dec4179496f37f26ccc4898f324816e6c7df0ed70 +size 2019379360 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q4_K_S.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q4_K_S.gguf new file mode 100644 index 0000000..dbd4a5f --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:145fe83e7874129a5660631e7e592b3261706aeb930c7883d9ab828bf820a9ff +size 1928202400 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q5_K_M.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q5_K_M.gguf new file mode 100644 index 0000000..feb2d8e --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d223bbe307343f84bbcdef9a350ae6910be399046a3e88bccddbb1c0b04708e7 +size 2322155680 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q5_K_S.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q5_K_S.gguf new file mode 100644 index 0000000..051a250 --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34a770d72cc318c8877f8e716b5bf52a73b254c72f186ec778f69abffe1acf47 +size 2269513888 diff --git a/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q6_K.gguf b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q6_K.gguf new file mode 100644 index 0000000..e9f0139 --- /dev/null +++ b/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:525d84d6b98e835753885c4ff29f2c36d3f467bf0ee5104fd6335fca532d83d1 +size 2643855520 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7643112 --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: mudler/LocalAI-functioncall-llama3.2-3b-v0.5 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/mudler/LocalAI-functioncall-llama3.2-3b-v0.5 + + +static quants are available at https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-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/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q4_1.gguf) | i1-Q4_1 | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-3b-v0.5-i1-GGUF/resolve/main/LocalAI-functioncall-llama3.2-3b-v0.5.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..51fbedf --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7fe85aafe8e2e9fee8941eed02cc526418e81d47cf18dad3d3e8be4b6f9c8a0 +size 2988377