commit af0c06cf79474fef82864e5c2294390d7d0db9ae Author: ModelHub XC Date: Tue Jul 21 15:52:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6767ede --- /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-Instruct-2507.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Instruct-2507.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-IQ1_M.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-IQ1_M.gguf new file mode 100644 index 0000000..2b53dcf --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ac6df876d6e87ec7e7eee54cfd2ad2f07e6445b097b5f5c81b26bc36925dfcb +size 7078291904 diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-IQ1_S.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-IQ1_S.gguf new file mode 100644 index 0000000..1c8e53a --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5038d6e11946775fbf6e13076e1b85593c0a833d020297de7a4a0483c70a15c +size 6416509376 diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-IQ2_M.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-IQ2_M.gguf new file mode 100644 index 0000000..a5b69c3 --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d126193054380b81b722e555a75c371d450dfc61a707878fb3d53baa8b940821 +size 10169508288 diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-IQ2_S.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-IQ2_S.gguf new file mode 100644 index 0000000..989e9db --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dae34929eec409498e4f35020b522f596a126243bcd037825a6532248f229a9b +size 9287131584 diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-IQ2_XS.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-IQ2_XS.gguf new file mode 100644 index 0000000..d5079f3 --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d382c5e689d005f97d16266942996211e64c376f70dbc7c521aecc63e74ad02 +size 9076222400 diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-IQ2_XXS.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..47852e6 --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c47183231e468237c5b5f6adfc3915946e544911737cf49842adc7314024e5a +size 8181262784 diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-IQ3_M.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-IQ3_M.gguf new file mode 100644 index 0000000..a3fb61e --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fc216aaf9fcc5e8296f81c385fc704a5538852a5d0589d49e8e8b2ab56124ea +size 13513062848 diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-IQ3_S.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-IQ3_S.gguf new file mode 100644 index 0000000..dd53033 --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87b61dafcec0ddb927dc22680a24cb5e625d6f37daec96335a35a5333a90ae1b +size 13299153344 diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-IQ3_XS.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-IQ3_XS.gguf new file mode 100644 index 0000000..b52338c --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4a8bb0399a34f848fbc1b7d27edda8cf714f4408247960639c987da943924a3 +size 12598442432 diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-IQ3_XXS.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..f5f9970 --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3af8fdd897fcb787ff8a352ad1a586d375978161326bf299df5d484fe9f55a73 +size 11849327040 diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-IQ4_XS.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-IQ4_XS.gguf new file mode 100644 index 0000000..edd087e --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7ae498669f11f4f9e12d08c62cad66f938d4dc0ea75d4a29d67b39c66f2a74b +size 16368349632 diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-Q2_K.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-Q2_K.gguf new file mode 100644 index 0000000..33b7550 --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:523111f27374c611e2cd557728ac69d218ada5d2f86201b375069dde251268b6 +size 11258610112 diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-Q2_K_S.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-Q2_K_S.gguf new file mode 100644 index 0000000..39bfa98 --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6b3568ac26c8cfee791f5b7ea8aac7a40c82d6977f5095e1b8361e69ce6fe3d +size 10519364032 diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-Q3_K_L.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-Q3_K_L.gguf new file mode 100644 index 0000000..0b17438 --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b58027142cf669ef24935fcb22aceb238cb5cb30d60a5387b2cb81bcb01b8f3 +size 15900670400 diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-Q3_K_M.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-Q3_K_M.gguf new file mode 100644 index 0000000..c6667be --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:176f28eafa3dd9ba9d94c2a9a29d4f4cae5f02029a962cae511d10b4f3e7a4d9 +size 14711847360 diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-Q3_K_S.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-Q3_K_S.gguf new file mode 100644 index 0000000..67642df --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dac6abf985f5d5d0791ba1d30cf6d659ed4885abdcdf971bc4a8788ba30039c4 +size 13292468672 diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-Q4_0.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-Q4_0.gguf new file mode 100644 index 0000000..0e1b821 --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c4b69d2ae36ce4ff562aa6575a7f5b0ad76abf89d8df1c68f7735466fd02014 +size 17379987904 diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-Q4_1.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-Q4_1.gguf new file mode 100644 index 0000000..1692f45 --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2425e8cc6e6ed94e08aa937ab71653ad9cab00b860e61bbb969c84c0dae747e6 +size 19192500672 diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-Q4_K_M.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-Q4_K_M.gguf new file mode 100644 index 0000000..23a0d0e --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4dac86ffa452e23083332e7de553c5087027242ed0263a83cdd00e73222d7ba +size 18556686784 diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-Q4_K_S.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-Q4_K_S.gguf new file mode 100644 index 0000000..869a289 --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:743b12708fc8ddb094bd5d787172fd498fa01fb3a6c938af41fd3938239a9d6d +size 17456009664 diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-Q5_K_M.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-Q5_K_M.gguf new file mode 100644 index 0000000..2ef71ff --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4081c434bc4782a5ccead3c37e54407a4729107c9c266abcd6432ee742988310 +size 21725581760 diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-Q5_K_S.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-Q5_K_S.gguf new file mode 100644 index 0000000..842b51e --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a013b464716dab2d7006c54b2729648bfda5281bc2c682a281c24ce2aea5782 +size 21080510912 diff --git a/Qwen3-30B-A3B-Instruct-2507.i1-Q6_K.gguf b/Qwen3-30B-A3B-Instruct-2507.i1-Q6_K.gguf new file mode 100644 index 0000000..38f6778 --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0024fe09b1e06d1ee503fc66fe495f83c99cab0472dd9df0450bb14da34b4290 +size 25092532672 diff --git a/Qwen3-30B-A3B-Instruct-2507.imatrix.gguf b/Qwen3-30B-A3B-Instruct-2507.imatrix.gguf new file mode 100644 index 0000000..efc23b4 --- /dev/null +++ b/Qwen3-30B-A3B-Instruct-2507.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f04d2d7a20bae5b663056014ca53207872a74f66a5779d0db549309d18049d9 +size 122029312 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ba944a6 --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: Qwen/Qwen3-30B-A3B-Instruct-2507 +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507/blob/main/LICENSE +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-30B-A3B-Instruct-2507-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-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-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.imatrix.gguf) | imatrix | 0.2 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.i1-IQ1_S.gguf) | i1-IQ1_S | 6.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.i1-IQ1_M.gguf) | i1-IQ1_M | 7.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 8.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.i1-IQ2_XS.gguf) | i1-IQ2_XS | 9.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.i1-IQ2_S.gguf) | i1-IQ2_S | 9.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.i1-IQ2_M.gguf) | i1-IQ2_M | 10.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.i1-Q2_K_S.gguf) | i1-Q2_K_S | 10.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.i1-Q2_K.gguf) | i1-Q2_K | 11.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 11.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.i1-IQ3_XS.gguf) | i1-IQ3_XS | 12.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.i1-Q3_K_S.gguf) | i1-Q3_K_S | 13.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.i1-IQ3_S.gguf) | i1-IQ3_S | 13.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.i1-IQ3_M.gguf) | i1-IQ3_M | 13.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.i1-Q3_K_M.gguf) | i1-Q3_K_M | 14.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.i1-Q3_K_L.gguf) | i1-Q3_K_L | 16.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.i1-IQ4_XS.gguf) | i1-IQ4_XS | 16.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.i1-Q4_0.gguf) | i1-Q4_0 | 17.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.i1-Q4_K_S.gguf) | i1-Q4_K_S | 17.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.i1-Q4_K_M.gguf) | i1-Q4_K_M | 18.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.i1-Q4_1.gguf) | i1-Q4_1 | 19.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.i1-Q5_K_S.gguf) | i1-Q5_K_S | 21.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.i1-Q5_K_M.gguf) | i1-Q5_K_M | 21.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Instruct-2507-i1-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507.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. + +