commit 71080ff9d4b56de49ae14104154c32c0437c0800 Author: ModelHub XC Date: Wed May 20 15:15:44 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b712b5a --- /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 +L3.2-Ascendant-Prime-16E-A6B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Ascendant-Prime-16E-A6B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-IQ1_M.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-IQ1_M.gguf new file mode 100644 index 0000000..760c3a9 --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb676fad94b8fd75664598528a76c0113f595b312adf92f1ad72d27eb1d2cc28 +size 8010541184 diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-IQ1_S.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-IQ1_S.gguf new file mode 100644 index 0000000..5705c4e --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaa21f777d25199ce7f75329bacb33bd88722549e9cb4d8e29f6467e21affe03 +size 7237871744 diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-IQ2_M.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-IQ2_M.gguf new file mode 100644 index 0000000..6adb261 --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6055a3c5c1fe9edbee0408bc479ba14fbb67a0c03a03e4f2723f89eeb1df2f3 +size 11526875264 diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-IQ2_S.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-IQ2_S.gguf new file mode 100644 index 0000000..afb045c --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:132f126f76261bfd65e8a8c23a116d26fde1cfbf7737c424debf0655a2fbd4a0 +size 10496649344 diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-IQ2_XS.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..8c07958 --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9689b80d99b347f6de873a4ada07cdf5587495dc37824ccaf494e349d56bc2e0 +size 10336807040 diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-IQ2_XXS.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..9de0bb7 --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a701218d4bda4bcc9eaa315cac03cc988f49d24b94e374cccfee36c3d9007f +size 9298323584 diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-IQ3_M.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-IQ3_M.gguf new file mode 100644 index 0000000..0f22e76 --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3af64e5e167357d604c6845fc3ddbcc992b0f204f02d5137318556178497223d +size 15380521088 diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-IQ3_S.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-IQ3_S.gguf new file mode 100644 index 0000000..1560038 --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bd62e01fe982456031231a245a834e338660b9cd3c7e3b994be1ec155454d9a +size 15173296256 diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-IQ3_XS.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..ca8e5b0 --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d898afd630c25be6f3b483a6e05a36620b18370918a0a2364045b78dff0a1cc +size 14364057728 diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-IQ3_XXS.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..a2601b3 --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:089031191fffcb361f42e3277c447c36d257299f16a79d2e810a0ffe6f56a7ae +size 13492856960 diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-IQ4_XS.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..2239c70 --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6e559f41d1a764005acda8afc620357f40b7b45db4347c613ee701bc4d7e32a +size 18679996544 diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-Q2_K.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-Q2_K.gguf new file mode 100644 index 0000000..0250e50 --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6679de51658d84ef98bbe902e0ccb5fa30c5598a64a573e7b379eceec570681a +size 12847423616 diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-Q2_K_S.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..e70be1b --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:805f02ea75b51ee97b80bb68ebc30c2fce8dbfb7f525e1612bb3056187d34f2e +size 11949711488 diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-Q3_K_L.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..9680ed2 --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:622b9b8c8aef9b519eddf6d268354c564a956886ef57c6ec365df4cd3a3636ca +size 18170781824 diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-Q3_K_M.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..6bdd9fd --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec115f5401034be6a38c4529deb74a3d6797b7debdaaf658e47b33c252bd9ae1 +size 16768573568 diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-Q3_K_S.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..44b60e0 --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7d4acd9f743dcc1f3c01c66be038790ee3983a0cfbf5de92c9c331e12215a0c +size 15173296256 diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-Q4_0.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-Q4_0.gguf new file mode 100644 index 0000000..a673d74 --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2ffae4e7359ae1e5252b076fe9777f9c3f04f9b97499936df01695c286e2c41 +size 19834478720 diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-Q4_1.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-Q4_1.gguf new file mode 100644 index 0000000..582d6b9 --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5261585bc326ffd153d448bd635fcc814e47958cd7ca36218748d82eb678d7b6 +size 21916950656 diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-Q4_K_M.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..961fe3c --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8c3f51e651e82b1a9ad578141665a2759bdc18733cee815cd53a704f081c242 +size 21223661696 diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-Q4_K_S.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..6685910 --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04e428983e9da917105b249d84910c2a106ba0030e496e05202bb0fb0f80627b +size 19911549056 diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-Q5_K_M.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..cdafd60 --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edf616f5264455d3c72307b0218ca6be744187fda295a2a18267447fd754f5c6 +size 24829452416 diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-Q5_K_S.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..06141b3 --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d250c6bb2ec103ab62aec125bb1001c821a9f2c1dde2a9009e5e0b7e8e3185a1 +size 24074920064 diff --git a/L3.2-Ascendant-Prime-16E-A6B.i1-Q6_K.gguf b/L3.2-Ascendant-Prime-16E-A6B.i1-Q6_K.gguf new file mode 100644 index 0000000..72fbc9d --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b0b2ca8bce74fb8320844a93d477067c48af6ea602485372194b66d034eb9eb +size 28660605056 diff --git a/L3.2-Ascendant-Prime-16E-A6B.imatrix.gguf b/L3.2-Ascendant-Prime-16E-A6B.imatrix.gguf new file mode 100644 index 0000000..1c0e6a6 --- /dev/null +++ b/L3.2-Ascendant-Prime-16E-A6B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:256640151c93298c9a891392729741971ed6014b9fe89430223a292adb03e423 +size 27450016 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1a03963 --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: blascotobasco/L3.2-Ascendant-Prime-16E-A6B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- moe +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/blascotobasco/L3.2-Ascendant-Prime-16E-A6B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#L3.2-Ascendant-Prime-16E-A6B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-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/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-IQ1_S.gguf) | i1-IQ1_S | 7.3 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-IQ1_M.gguf) | i1-IQ1_M | 8.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.4 | | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.4 | | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-IQ2_S.gguf) | i1-IQ2_S | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-IQ2_M.gguf) | i1-IQ2_M | 11.6 | | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 12.0 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-Q2_K.gguf) | i1-Q2_K | 12.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 13.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 14.5 | | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-IQ3_S.gguf) | i1-IQ3_S | 15.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 15.3 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-IQ3_M.gguf) | i1-IQ3_M | 15.5 | | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 18.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 18.8 | | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-Q4_0.gguf) | i1-Q4_0 | 19.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 20.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 21.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-Q4_1.gguf) | i1-Q4_1 | 22.0 | | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 24.2 | | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 24.9 | | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF/resolve/main/L3.2-Ascendant-Prime-16E-A6B.i1-Q6_K.gguf) | i1-Q6_K | 28.8 | 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. + +