commit f3a5e7b5842b3e7ea565f2f34584ef60ec0339ac Author: ModelHub XC Date: Tue Jul 21 11:55:10 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..762b9fc --- /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-Architect7.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Architect7.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-30B-A3B-Architect7.i1-IQ1_M.gguf b/Qwen3-30B-A3B-Architect7.i1-IQ1_M.gguf new file mode 100644 index 0000000..0b9bb4a --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56b527c4ea3e17f3697a86d67c2c58469ece4e142d25856375c078d44e56f8a9 +size 7077734336 diff --git a/Qwen3-30B-A3B-Architect7.i1-IQ1_S.gguf b/Qwen3-30B-A3B-Architect7.i1-IQ1_S.gguf new file mode 100644 index 0000000..f557465 --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc965079b93e498c99fb2e546481ab915d46bdff18e0f6e3de8ef8e98711cfb7 +size 6415951808 diff --git a/Qwen3-30B-A3B-Architect7.i1-IQ2_M.gguf b/Qwen3-30B-A3B-Architect7.i1-IQ2_M.gguf new file mode 100644 index 0000000..cc42b1f --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35d44c5c4e44e61c74fa390ab5a092c216d734f107084702232d09d411126846 +size 10168895200 diff --git a/Qwen3-30B-A3B-Architect7.i1-IQ2_S.gguf b/Qwen3-30B-A3B-Architect7.i1-IQ2_S.gguf new file mode 100644 index 0000000..6cc5130 --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:921b92e7d2f283d6930e1096596dedfcee977a9216d16353f8d12a0926aa97ce +size 9286518496 diff --git a/Qwen3-30B-A3B-Architect7.i1-IQ2_XS.gguf b/Qwen3-30B-A3B-Architect7.i1-IQ2_XS.gguf new file mode 100644 index 0000000..e4bf11f --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ac3561737bf263209675f2b0318434db26bd20c11c399a00e0ed78a3aaa4a1d +size 9075664832 diff --git a/Qwen3-30B-A3B-Architect7.i1-IQ2_XXS.gguf b/Qwen3-30B-A3B-Architect7.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..fc5b5fa --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caec4fa01588e1777d27b683e82c55bbfaf91c58de3617da1e3ea82469e01e84 +size 8180705216 diff --git a/Qwen3-30B-A3B-Architect7.i1-IQ3_M.gguf b/Qwen3-30B-A3B-Architect7.i1-IQ3_M.gguf new file mode 100644 index 0000000..4b535ff --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:591912164fd32bf89898640922f0d8311de0516dcd879b7c29a25ab5f1831700 +size 13512377152 diff --git a/Qwen3-30B-A3B-Architect7.i1-IQ3_S.gguf b/Qwen3-30B-A3B-Architect7.i1-IQ3_S.gguf new file mode 100644 index 0000000..08ea7e6 --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afbec1cb9a301b38b4f181cd18bbe310bf61a547119a1ce6a547bbe764f7f0ad +size 13298467648 diff --git a/Qwen3-30B-A3B-Architect7.i1-IQ3_XS.gguf b/Qwen3-30B-A3B-Architect7.i1-IQ3_XS.gguf new file mode 100644 index 0000000..dca8571 --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:860da8d628b8efc5cdc4e0ef626e40e66dc56781cebfc5a92abb7223912b04db +size 12597756736 diff --git a/Qwen3-30B-A3B-Architect7.i1-IQ3_XXS.gguf b/Qwen3-30B-A3B-Architect7.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..1205025 --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d5bbb81eb25b76d3f2cbb2f01ae338f3e8fad550fea8ed295c44a3e07882dba +size 11848713952 diff --git a/Qwen3-30B-A3B-Architect7.i1-IQ4_XS.gguf b/Qwen3-30B-A3B-Architect7.i1-IQ4_XS.gguf new file mode 100644 index 0000000..38fc8ce --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e496c96ae815d6cca593d017eb0a9c2b752333d7226ff2411da0fcb7e762ccfe +size 16367608384 diff --git a/Qwen3-30B-A3B-Architect7.i1-Q2_K.gguf b/Qwen3-30B-A3B-Architect7.i1-Q2_K.gguf new file mode 100644 index 0000000..d02eb28 --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adb2f6864188aacfc2d22b3cfa6934a3fe6e4817b4e2b0b3d764105a93615e1b +size 11257979936 diff --git a/Qwen3-30B-A3B-Architect7.i1-Q2_K_S.gguf b/Qwen3-30B-A3B-Architect7.i1-Q2_K_S.gguf new file mode 100644 index 0000000..e96e2b6 --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47e41990be2799d4d85eb65b48c59f3bf1016286bd3b1c71eb15b4a774b5906f +size 10518733856 diff --git a/Qwen3-30B-A3B-Architect7.i1-Q3_K_L.gguf b/Qwen3-30B-A3B-Architect7.i1-Q3_K_L.gguf new file mode 100644 index 0000000..dc18319 --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc1e0ad81f8d02cec300b0cb7159dcba3c2ef432e1571d4e752d2e01aca08631 +size 15899984704 diff --git a/Qwen3-30B-A3B-Architect7.i1-Q3_K_M.gguf b/Qwen3-30B-A3B-Architect7.i1-Q3_K_M.gguf new file mode 100644 index 0000000..fcb06a5 --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a13f88d559b84bff7ef626bbeaf1b5fe27300b94fe867d704895aa47b5699c6c +size 14711161664 diff --git a/Qwen3-30B-A3B-Architect7.i1-Q3_K_S.gguf b/Qwen3-30B-A3B-Architect7.i1-Q3_K_S.gguf new file mode 100644 index 0000000..18cb7e8 --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3de616cbad13c86f2ba906ab7c4aa01bcb903f2c63141650c2638e96acc4cedc +size 13291782976 diff --git a/Qwen3-30B-A3B-Architect7.i1-Q4_0.gguf b/Qwen3-30B-A3B-Architect7.i1-Q4_0.gguf new file mode 100644 index 0000000..202ffba --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:122b4d462ade9ead7c4f5b5cf5d0c7df026cc211e56d41ac126562128caa964c +size 17379229568 diff --git a/Qwen3-30B-A3B-Architect7.i1-Q4_1.gguf b/Qwen3-30B-A3B-Architect7.i1-Q4_1.gguf new file mode 100644 index 0000000..fad3a85 --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e26e291abcc8c2024545d03a71f124f40822677fdbb9cb59b6cdb2c6421cb425 +size 19191708160 diff --git a/Qwen3-30B-A3B-Architect7.i1-Q4_K_M.gguf b/Qwen3-30B-A3B-Architect7.i1-Q4_K_M.gguf new file mode 100644 index 0000000..022a1ce --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d34680f76b8236d68f4755d5a403cd33e0f93e8e2980cdab2d74fec06747214b +size 18555928448 diff --git a/Qwen3-30B-A3B-Architect7.i1-Q4_K_S.gguf b/Qwen3-30B-A3B-Architect7.i1-Q4_K_S.gguf new file mode 100644 index 0000000..146a50c --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:257a16b19b75e85113c06ccb7f4d70574d729e9f816b04bdc49d4844025b2307 +size 17455251328 diff --git a/Qwen3-30B-A3B-Architect7.i1-Q5_K_M.gguf b/Qwen3-30B-A3B-Architect7.i1-Q5_K_M.gguf new file mode 100644 index 0000000..fcdc9f0 --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e802eb33a6bf7fffadd39fd1ed09b7461fb7bcc50a2d8f5771e313db5888da1a +size 21724755072 diff --git a/Qwen3-30B-A3B-Architect7.i1-Q5_K_S.gguf b/Qwen3-30B-A3B-Architect7.i1-Q5_K_S.gguf new file mode 100644 index 0000000..8745c5f --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a41b2db2b15540d242d3bd7289c3e7ec905b3431dc77731db8c38491fc018153 +size 21079684224 diff --git a/Qwen3-30B-A3B-Architect7.i1-Q6_K.gguf b/Qwen3-30B-A3B-Architect7.i1-Q6_K.gguf new file mode 100644 index 0000000..42fd672 --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51367d95a289b2563dabd4850d6be3e2c9b0eb8d37c8b7c53c9672d238dffe6c +size 25091633376 diff --git a/Qwen3-30B-A3B-Architect7.imatrix.gguf b/Qwen3-30B-A3B-Architect7.imatrix.gguf new file mode 100644 index 0000000..bac0a34 --- /dev/null +++ b/Qwen3-30B-A3B-Architect7.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ba1534403fde62d31fc52b34b61d09ab2f83336dd185d511062a7a288b396ba +size 122029312 diff --git a/README.md b/README.md new file mode 100644 index 0000000..322d9a2 --- /dev/null +++ b/README.md @@ -0,0 +1,113 @@ +--- +base_model: nightmedia/Qwen3-30B-A3B-Architect7 +language: +- en +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- coding +- research +- deep thinking +- 256k context +- Qwen3 +- All use cases +- creative +- creative writing +- fiction writing +- plot generation +- sub-plot generation +- fiction writing +- story generation +- scene continue +- storytelling +- fiction story +- science fiction +- all genres +- story +- writing +- vivid prosing +- vivid writing +- fiction +- roleplaying +- bfloat16 +- finetune +- merge +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/nightmedia/Qwen3-30B-A3B-Architect7 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-30B-A3B-Architect7-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-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-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.imatrix.gguf) | imatrix | 0.2 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.i1-IQ1_S.gguf) | i1-IQ1_S | 6.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.i1-IQ1_M.gguf) | i1-IQ1_M | 7.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 8.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.i1-IQ2_XS.gguf) | i1-IQ2_XS | 9.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.i1-IQ2_S.gguf) | i1-IQ2_S | 9.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.i1-IQ2_M.gguf) | i1-IQ2_M | 10.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.i1-Q2_K_S.gguf) | i1-Q2_K_S | 10.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.i1-Q2_K.gguf) | i1-Q2_K | 11.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 11.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.i1-IQ3_XS.gguf) | i1-IQ3_XS | 12.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.i1-Q3_K_S.gguf) | i1-Q3_K_S | 13.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.i1-IQ3_S.gguf) | i1-IQ3_S | 13.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.i1-IQ3_M.gguf) | i1-IQ3_M | 13.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.i1-Q3_K_M.gguf) | i1-Q3_K_M | 14.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.i1-Q3_K_L.gguf) | i1-Q3_K_L | 16.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.i1-IQ4_XS.gguf) | i1-IQ4_XS | 16.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.i1-Q4_0.gguf) | i1-Q4_0 | 17.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.i1-Q4_K_S.gguf) | i1-Q4_K_S | 17.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.i1-Q4_K_M.gguf) | i1-Q4_K_M | 18.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.i1-Q4_1.gguf) | i1-Q4_1 | 19.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.i1-Q5_K_S.gguf) | i1-Q5_K_S | 21.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.i1-Q5_K_M.gguf) | i1-Q5_K_M | 21.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Architect7-i1-GGUF/resolve/main/Qwen3-30B-A3B-Architect7.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. + +