commit 0c235a9945b1b62df40951ec48ca84cc0b490386 Author: ModelHub XC Date: Tue May 26 23:10:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..766b093 --- /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 +Qwen3-30B-A3B-Architect5.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect5.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-30B-A3B-Architect5.i1-IQ1_M.gguf b/Qwen3-30B-A3B-Architect5.i1-IQ1_M.gguf new file mode 100644 index 0000000..29f2e19 --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06dbca03ce2d6558ebead3416d0ec49d13a3aaca8065c6789390cc63bf29d5af +size 7077731872 diff --git a/Qwen3-30B-A3B-Architect5.i1-IQ1_S.gguf b/Qwen3-30B-A3B-Architect5.i1-IQ1_S.gguf new file mode 100644 index 0000000..597cbd1 --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fc22f4fc2d9add0c5eb3f28bd0dff5f36dc840cc003e50ca959665cae0b081e +size 6415949344 diff --git a/Qwen3-30B-A3B-Architect5.i1-IQ2_M.gguf b/Qwen3-30B-A3B-Architect5.i1-IQ2_M.gguf new file mode 100644 index 0000000..51323ea --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:835eb0d752a7b7c55a4707dfff469bc7180424226a1891dbec825ec1762a91d0 +size 10168892736 diff --git a/Qwen3-30B-A3B-Architect5.i1-IQ2_S.gguf b/Qwen3-30B-A3B-Architect5.i1-IQ2_S.gguf new file mode 100644 index 0000000..a32226f --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2be5af90ca93fa4f2dec366ba3a08a18d84e354d4435d0b57ebfa81daf0a8a8 +size 9286516032 diff --git a/Qwen3-30B-A3B-Architect5.i1-IQ2_XS.gguf b/Qwen3-30B-A3B-Architect5.i1-IQ2_XS.gguf new file mode 100644 index 0000000..80663da --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63d304038c7d51f7d43b477235e736744e2ab9a5f0c09f154c88b5f322c55cad +size 9075662368 diff --git a/Qwen3-30B-A3B-Architect5.i1-IQ2_XXS.gguf b/Qwen3-30B-A3B-Architect5.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..773a68c --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94a2398a46a34ce761eedaac618ccae65806ad337de56c02a4846d5aad8cbeb8 +size 8180702752 diff --git a/Qwen3-30B-A3B-Architect5.i1-IQ3_M.gguf b/Qwen3-30B-A3B-Architect5.i1-IQ3_M.gguf new file mode 100644 index 0000000..a5a65fb --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56999437084bc9e8ecaf2d5fbd3be53d80b342406cd2b42721f1c426526e246c +size 13512374688 diff --git a/Qwen3-30B-A3B-Architect5.i1-IQ3_S.gguf b/Qwen3-30B-A3B-Architect5.i1-IQ3_S.gguf new file mode 100644 index 0000000..cc9b8f5 --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ae26c7fb9fe93754ebfcb6cb4c2ac95286c3e2c44b3620685c20ecc5008477c +size 13298465184 diff --git a/Qwen3-30B-A3B-Architect5.i1-IQ3_XS.gguf b/Qwen3-30B-A3B-Architect5.i1-IQ3_XS.gguf new file mode 100644 index 0000000..aa16ff6 --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec4151fd8b69ac93fa9f69210442fdc20541713d55b894888d1160e4172701ca +size 12597754272 diff --git a/Qwen3-30B-A3B-Architect5.i1-IQ3_XXS.gguf b/Qwen3-30B-A3B-Architect5.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..8723849 --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06caaa9e320ac2dcf39cab8c643c77e53e08fd9d9fb86f9c8b37b3defbcb932e +size 11848711488 diff --git a/Qwen3-30B-A3B-Architect5.i1-IQ4_XS.gguf b/Qwen3-30B-A3B-Architect5.i1-IQ4_XS.gguf new file mode 100644 index 0000000..43565fa --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7881ef37f4fd5358e5c396e12dfcbdcaac5f3fb5e3e20b5376deea06de3328a +size 16367605920 diff --git a/Qwen3-30B-A3B-Architect5.i1-Q2_K.gguf b/Qwen3-30B-A3B-Architect5.i1-Q2_K.gguf new file mode 100644 index 0000000..fe675b9 --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5b0a2da54e3c2942ac1ec47931c5e470da4f352511d395fecdc5763c77c4bd9 +size 11257977472 diff --git a/Qwen3-30B-A3B-Architect5.i1-Q2_K_S.gguf b/Qwen3-30B-A3B-Architect5.i1-Q2_K_S.gguf new file mode 100644 index 0000000..429a6ae --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8168d3483bdbb00aa86d6449b30490b9e901ab0233da16ae287b946ee0f93db +size 10518731392 diff --git a/Qwen3-30B-A3B-Architect5.i1-Q3_K_L.gguf b/Qwen3-30B-A3B-Architect5.i1-Q3_K_L.gguf new file mode 100644 index 0000000..ce9819a --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ba1d15a8a9909ffcd45081b2e4149c01bea6ee7ab36534d4234eccc00011005 +size 15899982240 diff --git a/Qwen3-30B-A3B-Architect5.i1-Q3_K_M.gguf b/Qwen3-30B-A3B-Architect5.i1-Q3_K_M.gguf new file mode 100644 index 0000000..15dd198 --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db51d201eeea84938b524f16e825578f99f87fcfb5c1f8ae32aa89b242d281b3 +size 14711159200 diff --git a/Qwen3-30B-A3B-Architect5.i1-Q3_K_S.gguf b/Qwen3-30B-A3B-Architect5.i1-Q3_K_S.gguf new file mode 100644 index 0000000..2fc2025 --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e21f333d784b67a2fc7479df6bc9ebfa50caeec394993bb08a6181bb4a20772a +size 13291780512 diff --git a/Qwen3-30B-A3B-Architect5.i1-Q4_0.gguf b/Qwen3-30B-A3B-Architect5.i1-Q4_0.gguf new file mode 100644 index 0000000..a5c163b --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01907039f28998bbef92dd8fd2715bfdfdb229f3751cf95965b2ab3edc973fc9 +size 17379227104 diff --git a/Qwen3-30B-A3B-Architect5.i1-Q4_1.gguf b/Qwen3-30B-A3B-Architect5.i1-Q4_1.gguf new file mode 100644 index 0000000..c4a95ec --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:762962a9f177179b6e9108a68c6470f8912f63cb2b90566bd6c35eceb67c63eb +size 19191705696 diff --git a/Qwen3-30B-A3B-Architect5.i1-Q4_K_M.gguf b/Qwen3-30B-A3B-Architect5.i1-Q4_K_M.gguf new file mode 100644 index 0000000..1777fae --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:607d557cdad512c0a9a0d64b60d0f72e787850a0c7685c56523cc0ac91f7bb90 +size 18555925984 diff --git a/Qwen3-30B-A3B-Architect5.i1-Q4_K_S.gguf b/Qwen3-30B-A3B-Architect5.i1-Q4_K_S.gguf new file mode 100644 index 0000000..0591cd2 --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f12426f996ad003d6ada82d7affff8a4c147edb56087aae9211810f614ea1baa +size 17455248864 diff --git a/Qwen3-30B-A3B-Architect5.i1-Q5_K_M.gguf b/Qwen3-30B-A3B-Architect5.i1-Q5_K_M.gguf new file mode 100644 index 0000000..83fd1dc --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cde082e6759b2c53ed3c36c83182775e50c82708582484c901434f434039a7be +size 21724752608 diff --git a/Qwen3-30B-A3B-Architect5.i1-Q5_K_S.gguf b/Qwen3-30B-A3B-Architect5.i1-Q5_K_S.gguf new file mode 100644 index 0000000..d9d3727 --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbc1aa24a5ccd0d7f325d048e9a9eb04d9591b4ea08bbe8cb060299c6be2330e +size 21079681760 diff --git a/Qwen3-30B-A3B-Architect5.i1-Q6_K.gguf b/Qwen3-30B-A3B-Architect5.i1-Q6_K.gguf new file mode 100644 index 0000000..a00f7c3 --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cfd9ab9676e416e7fbb7fa68876fb5a8e233cead0bf94b2e4b9c316aea81f50 +size 25091630912 diff --git a/Qwen3-30B-A3B-Architect5.imatrix.gguf b/Qwen3-30B-A3B-Architect5.imatrix.gguf new file mode 100644 index 0000000..6040d8d --- /dev/null +++ b/Qwen3-30B-A3B-Architect5.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4aa8647f7acd8f7db8bd9f34018f481a262172b66f42287a3d17cb374dadddf7 +size 122029312 diff --git a/README.md b/README.md new file mode 100644 index 0000000..28e8ad7 --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: nightmedia/Qwen3-30B-A3B-Architect5 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/nightmedia/Qwen3-30B-A3B-Architect5 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-30B-A3B-Architect5-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-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/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.imatrix.gguf) | imatrix | 0.2 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-IQ1_S.gguf) | i1-IQ1_S | 6.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-IQ1_M.gguf) | i1-IQ1_M | 7.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 8.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-IQ2_XS.gguf) | i1-IQ2_XS | 9.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-IQ2_S.gguf) | i1-IQ2_S | 9.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-IQ2_M.gguf) | i1-IQ2_M | 10.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-Q2_K_S.gguf) | i1-Q2_K_S | 10.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-Q2_K.gguf) | i1-Q2_K | 11.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 11.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-IQ3_XS.gguf) | i1-IQ3_XS | 12.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-Q3_K_S.gguf) | i1-Q3_K_S | 13.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-IQ3_S.gguf) | i1-IQ3_S | 13.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-IQ3_M.gguf) | i1-IQ3_M | 13.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-Q3_K_M.gguf) | i1-Q3_K_M | 14.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-Q3_K_L.gguf) | i1-Q3_K_L | 16.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-IQ4_XS.gguf) | i1-IQ4_XS | 16.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-Q4_0.gguf) | i1-Q4_0 | 17.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-Q4_K_S.gguf) | i1-Q4_K_S | 17.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-Q4_K_M.gguf) | i1-Q4_K_M | 18.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-Q4_1.gguf) | i1-Q4_1 | 19.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-Q5_K_S.gguf) | i1-Q5_K_S | 21.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-Q5_K_M.gguf) | i1-Q5_K_M | 21.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect5-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect5.i1-Q6_K.gguf) | i1-Q6_K | 25.2 | 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. + +