commit 1aea80aab7b3ab9e9c4dc5252f749881e683ab8f Author: ModelHub XC Date: Thu May 28 01:24:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..93d460b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +Qwen3-4B-Thinking-2507-MPOA.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-MPOA.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-IQ1_M.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ1_M.gguf new file mode 100644 index 0000000..68f503b --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1749a4ccefd09d00c946a8829462dd62bed9ec6d8e35c7fd1d140312e39007ce +size 1127018496 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-IQ1_S.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ1_S.gguf new file mode 100644 index 0000000..3fdf28b --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1a2ad9d168ef10f6e0658c0148a4a4cdcdf95fbce33e7b2c944e33d49b28bfc +size 1055256576 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-IQ2_M.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ2_M.gguf new file mode 100644 index 0000000..428daa7 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e28bcd3dd72344d1dbf6f2ed2ec5f9a5cb7824f25990dda6472e0cfbb151886 +size 1512984576 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-IQ2_S.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ2_S.gguf new file mode 100644 index 0000000..435e035 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffa44e1904384a49debc5a746845d30feda6a8a1d2111951553f112fe35e175e +size 1417302016 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-IQ2_XS.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ2_XS.gguf new file mode 100644 index 0000000..c7bd1bd --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b1e410ae87c9edc85eafb1e3853b3b28f8f7381e16f233c20fd313dd8bece9 +size 1354100736 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-IQ2_XXS.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..d5d6d97 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c4d537663a0f389be22f37974eefe557f0c07cb18c4d9aa74663ce372ff13af +size 1246621696 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-IQ3_M.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ3_M.gguf new file mode 100644 index 0000000..89df7fe --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01491797499dc300905fc86c03e64d2c8c0cc00e87254a91caa93f8fd4383b12 +size 1962896896 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-IQ3_S.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ3_S.gguf new file mode 100644 index 0000000..0bbe65c --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6fa9a69a71d9dfbcf504e4ea7b606312031f767667c373ca33930a18b5f8798 +size 1899531776 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-IQ3_XS.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ3_XS.gguf new file mode 100644 index 0000000..c86e65a --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:938f0b975054ab82d6d6e00ebefef8b4bd54eb7ee9d1d94bda57d58a87f5244d +size 1814375936 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-IQ3_XXS.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..560e3e6 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:233cffe56bdea7c35a5ef3200db2803f3cc4abeb6802d640587d5f73a4ed57e1 +size 1670189056 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-IQ4_NL.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ4_NL.gguf new file mode 100644 index 0000000..ed8d201 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1960e080b19112e2066a600d44a6a838c86c96ee236c75493e7882dbd3ce5ba0 +size 2381344256 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-IQ4_XS.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ4_XS.gguf new file mode 100644 index 0000000..7e78999 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59d6bfcbabde29c75e5e33049f87925e986b1e573809a09bc4a6a3fb09d66247 +size 2270752256 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-Q2_K.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-Q2_K.gguf new file mode 100644 index 0000000..e02d3ec --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c04688e51520f6c9d38abe849efb81c9bc8242447311f219a686c68a761f1a7 +size 1669500416 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-Q2_K_S.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-Q2_K_S.gguf new file mode 100644 index 0000000..b45b3ec --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe4976e95d34fd7cf104965185db3deb4af84d8cb60bc75af78ce04fe1bc2443 +size 1563454976 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-Q3_K_L.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-Q3_K_L.gguf new file mode 100644 index 0000000..4d9d645 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d9fefd6462ec324132368fed758e35238bc2757e6c89c8f1a79200ca9af9277 +size 2239786496 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-Q3_K_M.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-Q3_K_M.gguf new file mode 100644 index 0000000..0eac0f5 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f30fbd83d59e1cad2d4bd3903197727da0cd12462a72111b4d7a8b19e994b6df +size 2075618816 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-Q3_K_S.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-Q3_K_S.gguf new file mode 100644 index 0000000..280a036 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2627f36a6668c77aceab94b7b7a8d7db15663c9a58e0be403fa73a55ecee3d55 +size 1886998016 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-Q4_0.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-Q4_0.gguf new file mode 100644 index 0000000..175ff43 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34575c5c6a2c28c45dac932505f6208327f765a5d6bb143aa1dc871927f447c2 +size 2375773696 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-Q4_1.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-Q4_1.gguf new file mode 100644 index 0000000..4f1721c --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba0024b3934e6ba1f201d1355fb9aa93162c65ea3f9d2352fcd5e50ec4e0c38a +size 2596630016 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-Q4_K_M.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-Q4_K_M.gguf new file mode 100644 index 0000000..e05bb51 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:effaff4d56b931eb41f8c4ab18f851a16f11b706fa8f5c1518cf3459754930c0 +size 2497281536 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-Q4_K_S.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-Q4_K_S.gguf new file mode 100644 index 0000000..e1e76cc --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41f3c0d0f360cc06284679f2b7f337ff3dc0a8f13b06974950d81cacbfeecf3a +size 2383310336 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-Q5_K_M.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-Q5_K_M.gguf new file mode 100644 index 0000000..29b3fce --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ee800eab9b60e7f15156b4a59ed85da24e1e6e4675db940191a6b9ee037a414 +size 2889514496 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-Q5_K_S.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-Q5_K_S.gguf new file mode 100644 index 0000000..bc82e6d --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d38c6f90b9ac97d45728e7ecdbb031c496a61a4dc4716c505340093bdcd7228 +size 2823712256 diff --git a/Qwen3-4B-Thinking-2507-MPOA.i1-Q6_K.gguf b/Qwen3-4B-Thinking-2507-MPOA.i1-Q6_K.gguf new file mode 100644 index 0000000..bf1e2ff --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8909540d1481a25b286c3f7a0008f96323070caec0e82c7e28404a8f42143cdf +size 3306262016 diff --git a/Qwen3-4B-Thinking-2507-MPOA.imatrix.gguf b/Qwen3-4B-Thinking-2507-MPOA.imatrix.gguf new file mode 100644 index 0000000..25bcc31 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-MPOA.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1887b9383ada72417075153edbff88f0fb367ef6be36ade5ba7d396c26f538de +size 3872640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fcc7e09 --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: YanLabs/Qwen3-4B-Thinking-2507-MPOA +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/YanLabs/Qwen3-4B-Thinking-2507-MPOA + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Thinking-2507-MPOA-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-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/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-MPOA-i1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-MPOA.i1-Q6_K.gguf) | i1-Q6_K | 3.4 | 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. + +