commit 9a84b57b6611788cf392ed3755e9c51828451d4d Author: ModelHub XC Date: Wed May 27 04:10:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-30B-A3B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0576a99 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,52 @@ +*.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 +Qwen3-30B-A3B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-30B-A3B.i1-IQ3_M.gguf b/Qwen3-30B-A3B.i1-IQ3_M.gguf new file mode 100644 index 0000000..859ea44 --- /dev/null +++ b/Qwen3-30B-A3B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbe463501bcbd136999e29b721babaec09ad2d54641d379a24f63de8f5ea358d +size 13513062976 diff --git a/Qwen3-30B-A3B.i1-IQ3_S.gguf b/Qwen3-30B-A3B.i1-IQ3_S.gguf new file mode 100644 index 0000000..c84b4bd --- /dev/null +++ b/Qwen3-30B-A3B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e6af389694c3774b6f1c425360d9e0f3b1bf6905bec9d0fcc69313683c3b9b4 +size 13299153472 diff --git a/Qwen3-30B-A3B.i1-IQ3_XS.gguf b/Qwen3-30B-A3B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..babb6bd --- /dev/null +++ b/Qwen3-30B-A3B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d82967d6786c98cdb7740257a0f0a90fe7d03bcb413fa7c42749edcc62f48478 +size 12598442560 diff --git a/Qwen3-30B-A3B.i1-IQ3_XXS.gguf b/Qwen3-30B-A3B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..3347a6c --- /dev/null +++ b/Qwen3-30B-A3B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a67b77e9396c479a9f833383adc00ca758c54eb2cbf3332cd76f73918ca888b7 +size 11849327168 diff --git a/Qwen3-30B-A3B.i1-IQ4_XS.gguf b/Qwen3-30B-A3B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..b849843 --- /dev/null +++ b/Qwen3-30B-A3B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a03915cc28aa8872799cea4599ffd47b953bc152a247e7c87ecb236cbc010bf +size 16368349760 diff --git a/Qwen3-30B-A3B.i1-Q2_K.gguf b/Qwen3-30B-A3B.i1-Q2_K.gguf new file mode 100644 index 0000000..b428667 --- /dev/null +++ b/Qwen3-30B-A3B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8582f15b811b65e7cb701c494b7354fe95b4688e84f6a8e5f5b0736499252281 +size 11258610240 diff --git a/Qwen3-30B-A3B.i1-Q3_K_L.gguf b/Qwen3-30B-A3B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..3f60fea --- /dev/null +++ b/Qwen3-30B-A3B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fd81d24c39e7c9c065267af7611cdd938f95a4c5ba72db70011cc1090374da3 +size 15900670528 diff --git a/Qwen3-30B-A3B.i1-Q3_K_M.gguf b/Qwen3-30B-A3B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..f672d97 --- /dev/null +++ b/Qwen3-30B-A3B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e054434c8b18b79736d0b66a93006254cb6d39134e9999252641af092fe99a0e +size 14711847488 diff --git a/Qwen3-30B-A3B.i1-Q3_K_S.gguf b/Qwen3-30B-A3B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..7538505 --- /dev/null +++ b/Qwen3-30B-A3B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9d5124f88c18386a5225895317c3f2ecd9b6fa8d95808e58e566922d035a340 +size 13292468800 diff --git a/Qwen3-30B-A3B.i1-Q4_0.gguf b/Qwen3-30B-A3B.i1-Q4_0.gguf new file mode 100644 index 0000000..0a6504e --- /dev/null +++ b/Qwen3-30B-A3B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af683b356178546de5334eeb083f450a3c1b39dacd58a9e4d6bed8f71be96717 +size 17379988032 diff --git a/Qwen3-30B-A3B.i1-Q4_1.gguf b/Qwen3-30B-A3B.i1-Q4_1.gguf new file mode 100644 index 0000000..11d6f70 --- /dev/null +++ b/Qwen3-30B-A3B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:835c14d87d3f99ff3b7b3d91eb08862adc0a4dff9db4926db8b0ca405146f5d1 +size 19192500800 diff --git a/Qwen3-30B-A3B.i1-Q4_K_M.gguf b/Qwen3-30B-A3B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..f1170eb --- /dev/null +++ b/Qwen3-30B-A3B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:453ae13d0cdb8f590f806ee59ce94f6d615f4ad18fbde8e02f7247203d4107f3 +size 18556686912 diff --git a/Qwen3-30B-A3B.i1-Q4_K_S.gguf b/Qwen3-30B-A3B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..28bbbe7 --- /dev/null +++ b/Qwen3-30B-A3B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0bcc2220162ec8f9146660eff2b96d6a68f94eb7227ebce0e20ea1a1b455013 +size 17456009792 diff --git a/Qwen3-30B-A3B.i1-Q5_K_M.gguf b/Qwen3-30B-A3B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..25e9437 --- /dev/null +++ b/Qwen3-30B-A3B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8645a96f350aaf105b41fa2a82f8ad3acb511bb8c19f20aace84fae11364ef89 +size 21725581888 diff --git a/Qwen3-30B-A3B.i1-Q5_K_S.gguf b/Qwen3-30B-A3B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..2bcfce3 --- /dev/null +++ b/Qwen3-30B-A3B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e72dc3e978671bb94a31354d6d5916a4cd58def7db0dc5a0a9fcd6159df5c02 +size 21080511040 diff --git a/Qwen3-30B-A3B.i1-Q6_K.gguf b/Qwen3-30B-A3B.i1-Q6_K.gguf new file mode 100644 index 0000000..a2d7538 --- /dev/null +++ b/Qwen3-30B-A3B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:641f74f912cf5c57b6b7325cacc284992d8d320e6dffca25b6c2b271ca269e31 +size 25092532800 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f73c94f --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Qwen/Qwen3-30B-A3B +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen3-30B-A3B/blob/main/LICENSE +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Qwen/Qwen3-30B-A3B + + +static quants are available at https://huggingface.co/mradermacher/Qwen3-30B-A3B-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-i1-GGUF/resolve/main/Qwen3-30B-A3B.i1-Q2_K.gguf) | i1-Q2_K | 11.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-i1-GGUF/resolve/main/Qwen3-30B-A3B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 11.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-i1-GGUF/resolve/main/Qwen3-30B-A3B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 12.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-i1-GGUF/resolve/main/Qwen3-30B-A3B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 13.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-i1-GGUF/resolve/main/Qwen3-30B-A3B.i1-IQ3_S.gguf) | i1-IQ3_S | 13.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-i1-GGUF/resolve/main/Qwen3-30B-A3B.i1-IQ3_M.gguf) | i1-IQ3_M | 13.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-i1-GGUF/resolve/main/Qwen3-30B-A3B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 14.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-i1-GGUF/resolve/main/Qwen3-30B-A3B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 16.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-i1-GGUF/resolve/main/Qwen3-30B-A3B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 16.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-i1-GGUF/resolve/main/Qwen3-30B-A3B.i1-Q4_0.gguf) | i1-Q4_0 | 17.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-i1-GGUF/resolve/main/Qwen3-30B-A3B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 17.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-i1-GGUF/resolve/main/Qwen3-30B-A3B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 18.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-i1-GGUF/resolve/main/Qwen3-30B-A3B.i1-Q4_1.gguf) | i1-Q4_1 | 19.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-i1-GGUF/resolve/main/Qwen3-30B-A3B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 21.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-i1-GGUF/resolve/main/Qwen3-30B-A3B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 21.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-i1-GGUF/resolve/main/Qwen3-30B-A3B.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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..28fb6bf --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:641314e89d6947add129cc0e4dca5602d16abf72623c31320210a9bc1185ff00 +size 116929677