commit 5c977943930021943ae0e8eb74ffed2d04cc864e Author: ModelHub XC Date: Fri May 8 19:14:04 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0c88bc0 --- /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 +ASTRA-32B-Thinking-v1.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +ASTRA-32B-Thinking-v1.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ASTRA-32B-Thinking-v1.i1-IQ1_M.gguf b/ASTRA-32B-Thinking-v1.i1-IQ1_M.gguf new file mode 100644 index 0000000..0c56896 --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68c59565b49fe1be82309de00d5248446aaafb07874d6c0f304e604006cfb702 +size 7959868960 diff --git a/ASTRA-32B-Thinking-v1.i1-IQ1_S.gguf b/ASTRA-32B-Thinking-v1.i1-IQ1_S.gguf new file mode 100644 index 0000000..f1f2fde --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d1c2b0d02b76f8b9824b1c7e568c33653f75891057268db4f6b476fab95b9af +size 7323842080 diff --git a/ASTRA-32B-Thinking-v1.i1-IQ2_M.gguf b/ASTRA-32B-Thinking-v1.i1-IQ2_M.gguf new file mode 100644 index 0000000..35f2fc9 --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48b0b5066fde88c42e029e39ec5b16ea3752377d1614d50893af6d40e9301fc8 +size 11362861600 diff --git a/ASTRA-32B-Thinking-v1.i1-IQ2_S.gguf b/ASTRA-32B-Thinking-v1.i1-IQ2_S.gguf new file mode 100644 index 0000000..0986388 --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7ee34ad1fcd5cf47c1e299b37edc73166a42209ed4a8db832a34fd808e0b7b5 +size 10514825760 diff --git a/ASTRA-32B-Thinking-v1.i1-IQ2_XS.gguf b/ASTRA-32B-Thinking-v1.i1-IQ2_XS.gguf new file mode 100644 index 0000000..3a63d07 --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a08d1a73a911c0dc6288568844d933a40ad0c8deb32a88085598eeb2f33257a +size 9951835680 diff --git a/ASTRA-32B-Thinking-v1.i1-IQ2_XXS.gguf b/ASTRA-32B-Thinking-v1.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..ae19a56 --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c42171074133ffd9d86357c52a394f751d375f235fc1e3a6453b7db30db254b +size 9019913760 diff --git a/ASTRA-32B-Thinking-v1.i1-IQ3_M.gguf b/ASTRA-32B-Thinking-v1.i1-IQ3_M.gguf new file mode 100644 index 0000000..b2a42f8 --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be8d85b339b02b5833b4996617f446d967320a1023b3e883ee5af51952f380cd +size 14930083360 diff --git a/ASTRA-32B-Thinking-v1.i1-IQ3_S.gguf b/ASTRA-32B-Thinking-v1.i1-IQ3_S.gguf new file mode 100644 index 0000000..fbd990e --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b12211498a8030a669305443ac4f4b1e6849964641b04ebb233e6af9f0065e39 +size 14434303520 diff --git a/ASTRA-32B-Thinking-v1.i1-IQ3_XS.gguf b/ASTRA-32B-Thinking-v1.i1-IQ3_XS.gguf new file mode 100644 index 0000000..168f349 --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:098a402f8097bfd5d350796861fbffc0e105523940757b4fbbcecc47de3b2d5e +size 13702921760 diff --git a/ASTRA-32B-Thinking-v1.i1-IQ3_XXS.gguf b/ASTRA-32B-Thinking-v1.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..9eee069 --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8511a04aa699b7c1f4fb98db9892740be371e4c25ae35ec6bdd9d6cb710f6df4 +size 12821037600 diff --git a/ASTRA-32B-Thinking-v1.i1-IQ4_XS.gguf b/ASTRA-32B-Thinking-v1.i1-IQ4_XS.gguf new file mode 100644 index 0000000..aa57d55 --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80df9b7e94978000aeab34126cb4cb161ad4ce3164b5ad515e603aed7f3fa4bb +size 17690495520 diff --git a/ASTRA-32B-Thinking-v1.i1-Q2_K.gguf b/ASTRA-32B-Thinking-v1.i1-Q2_K.gguf new file mode 100644 index 0000000..2e18b6c --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:399c46926ee89b503304870006cae0f9c785f35b7b57238d03743e2998b1b253 +size 12344652320 diff --git a/ASTRA-32B-Thinking-v1.i1-Q2_K_S.gguf b/ASTRA-32B-Thinking-v1.i1-Q2_K_S.gguf new file mode 100644 index 0000000..c49bfa0 --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bb9e2a63b686ecab13fcaed8fcf7708ba8befbe0529fa77062cd45ca4ba4049 +size 11465814560 diff --git a/ASTRA-32B-Thinking-v1.i1-Q3_K_L.gguf b/ASTRA-32B-Thinking-v1.i1-Q3_K_L.gguf new file mode 100644 index 0000000..31dd7e1 --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1955f7c45d0f0db1d5505299e4415495d8e15cadc1255194fdde0d33a8b24ae8 +size 17330994720 diff --git a/ASTRA-32B-Thinking-v1.i1-Q3_K_M.gguf b/ASTRA-32B-Thinking-v1.i1-Q3_K_M.gguf new file mode 100644 index 0000000..e01a33e --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f6f364a362f97aa008871733090eab46114befacc148bbeffbb951dacc83bc4 +size 15971778080 diff --git a/ASTRA-32B-Thinking-v1.i1-Q3_K_S.gguf b/ASTRA-32B-Thinking-v1.i1-Q3_K_S.gguf new file mode 100644 index 0000000..a1ee82f --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b024837edaa290bea79ca6c30b81cdcbd55168e422a1481af3706b93cec4c46 +size 14389739040 diff --git a/ASTRA-32B-Thinking-v1.i1-Q4_0.gguf b/ASTRA-32B-Thinking-v1.i1-Q4_0.gguf new file mode 100644 index 0000000..7259ad2 --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06bb91c345ec95f8938f0a525ee5da37c5e2ed4105918739816778cf4b0ab806 +size 18703088160 diff --git a/ASTRA-32B-Thinking-v1.i1-Q4_1.gguf b/ASTRA-32B-Thinking-v1.i1-Q4_1.gguf new file mode 100644 index 0000000..016eda4 --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a601b954fbb3a14ac102b19e3af3be5c70a1d2b4b194b4431aaf26a27766b88 +size 20636523040 diff --git a/ASTRA-32B-Thinking-v1.i1-Q4_K_M.gguf b/ASTRA-32B-Thinking-v1.i1-Q4_K_M.gguf new file mode 100644 index 0000000..6abfa90 --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60ccac0b4277ad1467ecdb52492ab9ec0bd62a1e8b8b3288d197d66613d51719 +size 19762149920 diff --git a/ASTRA-32B-Thinking-v1.i1-Q4_K_S.gguf b/ASTRA-32B-Thinking-v1.i1-Q4_K_S.gguf new file mode 100644 index 0000000..c56aab9 --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de9414ba4dd6165c6f80e30e7a4903fe7e914ec14ff2ebe13e069b4dcfb05bd1 +size 18771245600 diff --git a/ASTRA-32B-Thinking-v1.i1-Q5_K_M.gguf b/ASTRA-32B-Thinking-v1.i1-Q5_K_M.gguf new file mode 100644 index 0000000..f685b8c --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b5196dcea744ab38b5f1cd815aeec386ce7260ba84837ea2f8a887f9db06bd1 +size 23214832160 diff --git a/ASTRA-32B-Thinking-v1.i1-Q5_K_S.gguf b/ASTRA-32B-Thinking-v1.i1-Q5_K_S.gguf new file mode 100644 index 0000000..e6f4696 --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb693352661ff498cf164c389d359e4db215b731fde64c532f06984193b737fb +size 22635493920 diff --git a/ASTRA-32B-Thinking-v1.i1-Q6_K.gguf b/ASTRA-32B-Thinking-v1.i1-Q6_K.gguf new file mode 100644 index 0000000..3ce45fd --- /dev/null +++ b/ASTRA-32B-Thinking-v1.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20fa7cb39783f0201ca86799539e17324ea7823e785151beff81121ce55f0bf0 +size 26883307040 diff --git a/ASTRA-32B-Thinking-v1.imatrix.gguf b/ASTRA-32B-Thinking-v1.imatrix.gguf new file mode 100644 index 0000000..3606500 --- /dev/null +++ b/ASTRA-32B-Thinking-v1.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4d171b25a935a2b327209d525dc923e244db59f86457677609c687f5cfeddf5 +size 15273216 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0c5e6fa --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: Emperorizzis/ASTRA-32B-Thinking-v1 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/Emperorizzis/ASTRA-32B-Thinking-v1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ASTRA-32B-Thinking-v1-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-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/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-IQ1_M.gguf) | i1-IQ1_M | 8.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-IQ2_S.gguf) | i1-IQ2_S | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-IQ2_M.gguf) | i1-IQ2_M | 11.5 | | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-IQ3_S.gguf) | i1-IQ3_S | 14.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-IQ3_M.gguf) | i1-IQ3_M | 15.0 | | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 19.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-Q4_1.gguf) | i1-Q4_1 | 20.7 | | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.3 | | +| [GGUF](https://huggingface.co/mradermacher/ASTRA-32B-Thinking-v1-i1-GGUF/resolve/main/ASTRA-32B-Thinking-v1.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | 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. + +