commit 08ca8718fa06e9a826d72093ec992c60378072b7 Author: ModelHub XC Date: Wed May 27 09:25:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Exp2-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a1b4b0d --- /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-Exp2.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Exp2.i1-IQ1_M.gguf b/Qwen3-4B-Exp2.i1-IQ1_M.gguf new file mode 100644 index 0000000..8f63749 --- /dev/null +++ b/Qwen3-4B-Exp2.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64317d6ba6baa957101bb428afb42dca829b172f8a7cd9868d498f3cdfd12e12 +size 1254640288 diff --git a/Qwen3-4B-Exp2.i1-IQ1_S.gguf b/Qwen3-4B-Exp2.i1-IQ1_S.gguf new file mode 100644 index 0000000..dab5407 --- /dev/null +++ b/Qwen3-4B-Exp2.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:929b28e7fe965465264d23019b1f6a53eb1f512c5531154e379c7708bc623ba7 +size 1182878368 diff --git a/Qwen3-4B-Exp2.i1-IQ2_M.gguf b/Qwen3-4B-Exp2.i1-IQ2_M.gguf new file mode 100644 index 0000000..3577a1b --- /dev/null +++ b/Qwen3-4B-Exp2.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:375493f2c53c6e824f9d2ab5523f3e1622acbc0853cb1f266dad6d003b969824 +size 1680109728 diff --git a/Qwen3-4B-Exp2.i1-IQ2_S.gguf b/Qwen3-4B-Exp2.i1-IQ2_S.gguf new file mode 100644 index 0000000..6197b47 --- /dev/null +++ b/Qwen3-4B-Exp2.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cf673787f1f2e2dd5c70da813663648e7f72a45cc8f044a98cb6aaa206b9ae0 +size 1584427168 diff --git a/Qwen3-4B-Exp2.i1-IQ2_XS.gguf b/Qwen3-4B-Exp2.i1-IQ2_XS.gguf new file mode 100644 index 0000000..93b1d03 --- /dev/null +++ b/Qwen3-4B-Exp2.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0daa3b0d1be5873c9db4ef1d52bb581d132f4c26473e8bdad0623a62cd48df66 +size 1481722528 diff --git a/Qwen3-4B-Exp2.i1-IQ2_XXS.gguf b/Qwen3-4B-Exp2.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..b65d01f --- /dev/null +++ b/Qwen3-4B-Exp2.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba2deab53581d7129918224ced29fd00ad25e49a670c6113319186cafb1c3cda +size 1374243488 diff --git a/Qwen3-4B-Exp2.i1-IQ3_M.gguf b/Qwen3-4B-Exp2.i1-IQ3_M.gguf new file mode 100644 index 0000000..6a295d0 --- /dev/null +++ b/Qwen3-4B-Exp2.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db33933b7c87e8bfd7b5e46b3a606d981809a3bb38e7ee2ad6910b4ff424ae71 +size 2130022048 diff --git a/Qwen3-4B-Exp2.i1-IQ3_S.gguf b/Qwen3-4B-Exp2.i1-IQ3_S.gguf new file mode 100644 index 0000000..b762ea3 --- /dev/null +++ b/Qwen3-4B-Exp2.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eef031be0acd40ecf609576c0ea6b0417fff650ba6ff69601152939c84086978 +size 2066656928 diff --git a/Qwen3-4B-Exp2.i1-IQ3_XS.gguf b/Qwen3-4B-Exp2.i1-IQ3_XS.gguf new file mode 100644 index 0000000..10f8d1a --- /dev/null +++ b/Qwen3-4B-Exp2.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:736c5b383843f498a50c249db0ca878db620abd0064560d8b758e2e5a2b60faa +size 1981501088 diff --git a/Qwen3-4B-Exp2.i1-IQ3_XXS.gguf b/Qwen3-4B-Exp2.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..3254b8a --- /dev/null +++ b/Qwen3-4B-Exp2.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8584e236360fa83a764eb30fed424a694b6de045de0cac0d9dc81d794b226b81 +size 1837314208 diff --git a/Qwen3-4B-Exp2.i1-IQ4_NL.gguf b/Qwen3-4B-Exp2.i1-IQ4_NL.gguf new file mode 100644 index 0000000..908874b --- /dev/null +++ b/Qwen3-4B-Exp2.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:257c770b28a91f4c2c8355090158c1c5111eb83ef90569d2269b8bef30ab447a +size 2600127648 diff --git a/Qwen3-4B-Exp2.i1-IQ4_XS.gguf b/Qwen3-4B-Exp2.i1-IQ4_XS.gguf new file mode 100644 index 0000000..3707908 --- /dev/null +++ b/Qwen3-4B-Exp2.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b3e84796f862a70d8d924a62272f15b4f4bc26c5fcab8c9d87f7913134fd3e9 +size 2477380768 diff --git a/Qwen3-4B-Exp2.i1-Q2_K.gguf b/Qwen3-4B-Exp2.i1-Q2_K.gguf new file mode 100644 index 0000000..78ccf1f --- /dev/null +++ b/Qwen3-4B-Exp2.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a542d9a9e39fbb813d8c7e747de9952fb842ee951ac13452ede3e0360fe5a3e +size 1797122208 diff --git a/Qwen3-4B-Exp2.i1-Q2_K_S.gguf b/Qwen3-4B-Exp2.i1-Q2_K_S.gguf new file mode 100644 index 0000000..dc0d20b --- /dev/null +++ b/Qwen3-4B-Exp2.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:097d4ab188f939199047388c4cb25e71f3919af8f54e754254722e3e29e3916f +size 1691076768 diff --git a/Qwen3-4B-Exp2.i1-Q3_K_L.gguf b/Qwen3-4B-Exp2.i1-Q3_K_L.gguf new file mode 100644 index 0000000..28ee177 --- /dev/null +++ b/Qwen3-4B-Exp2.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e98e625779e8d1449975be0a478b37b49bffa5f1abbfc80124eade54e2fc369 +size 2406911648 diff --git a/Qwen3-4B-Exp2.i1-Q3_K_M.gguf b/Qwen3-4B-Exp2.i1-Q3_K_M.gguf new file mode 100644 index 0000000..fdfc7a8 --- /dev/null +++ b/Qwen3-4B-Exp2.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f519da5c77d77a4217380f1e8e3851dddc0e0cac7b3c2fe2bd732b340ee5b8c +size 2242743968 diff --git a/Qwen3-4B-Exp2.i1-Q3_K_S.gguf b/Qwen3-4B-Exp2.i1-Q3_K_S.gguf new file mode 100644 index 0000000..0b87069 --- /dev/null +++ b/Qwen3-4B-Exp2.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beb4b51e31225f05ab8bb1bc2ea83f55d6535275df25668c5b286541a259da3c +size 2054123168 diff --git a/Qwen3-4B-Exp2.i1-Q4_0.gguf b/Qwen3-4B-Exp2.i1-Q4_0.gguf new file mode 100644 index 0000000..909085f --- /dev/null +++ b/Qwen3-4B-Exp2.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac635d479342663455598f8256d061f43250a49e3bb30c8a0cbccb1870365d33 +size 2594557088 diff --git a/Qwen3-4B-Exp2.i1-Q4_1.gguf b/Qwen3-4B-Exp2.i1-Q4_1.gguf new file mode 100644 index 0000000..bd351af --- /dev/null +++ b/Qwen3-4B-Exp2.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d82712d94a63e85b57992282be33c0fe5fc50c7399c2e6fb9357a36ccc7fa8ef +size 2839723168 diff --git a/Qwen3-4B-Exp2.i1-Q4_K_M.gguf b/Qwen3-4B-Exp2.i1-Q4_K_M.gguf new file mode 100644 index 0000000..175f97a --- /dev/null +++ b/Qwen3-4B-Exp2.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7330e84604da048538786682b672c034afae1a988df65d62321c247c13dddcb4 +size 2716064928 diff --git a/Qwen3-4B-Exp2.i1-Q4_K_S.gguf b/Qwen3-4B-Exp2.i1-Q4_K_S.gguf new file mode 100644 index 0000000..9e726b8 --- /dev/null +++ b/Qwen3-4B-Exp2.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af0a5f9a6f9660685ae31b155cca45f235dd3b516d114598d84032118dc1604e +size 2602093728 diff --git a/Qwen3-4B-Exp2.i1-Q5_K_M.gguf b/Qwen3-4B-Exp2.i1-Q5_K_M.gguf new file mode 100644 index 0000000..386ae51 --- /dev/null +++ b/Qwen3-4B-Exp2.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09d4b77e07b90a75968ca359729ca9939f94c3d49432a9f2f974c94747e32260 +size 3156917408 diff --git a/Qwen3-4B-Exp2.i1-Q5_K_S.gguf b/Qwen3-4B-Exp2.i1-Q5_K_S.gguf new file mode 100644 index 0000000..27476be --- /dev/null +++ b/Qwen3-4B-Exp2.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:306a3a54400dbeb99a32bc01e146c3b7e18b302448f997f7f44a1c1e034ab870 +size 3091115168 diff --git a/Qwen3-4B-Exp2.i1-Q6_K.gguf b/Qwen3-4B-Exp2.i1-Q6_K.gguf new file mode 100644 index 0000000..569009c --- /dev/null +++ b/Qwen3-4B-Exp2.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ebd99ab8e0868510b03c6ced0228318e08568dd5945ea7dca2836f6805affb0 +size 3625323168 diff --git a/Qwen3-4B-Exp2.imatrix.gguf b/Qwen3-4B-Exp2.imatrix.gguf new file mode 100644 index 0000000..30e4998 --- /dev/null +++ b/Qwen3-4B-Exp2.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:944f7272a6443d6ca3c7a7db355297f2ccd642eb4185f10a13bed862a236599d +size 3872640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..46618d3 --- /dev/null +++ b/README.md @@ -0,0 +1,92 @@ +--- +base_model: bunnycore/Qwen3-4B-Exp2 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- beyoru/Qwen3-4B-I-1509 +- TeichAI/Qwen3-4B-Instruct-2507-Claude-Opus-3-Distill +- bunnycore/Qwen3-4B-Exp +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/bunnycore/Qwen3-4B-Exp2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Exp2-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-4B-Exp2-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-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-IQ1_S.gguf) | i1-IQ1_S | 1.3 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-IQ1_M.gguf) | i1-IQ1_M | 1.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-IQ2_S.gguf) | i1-IQ2_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-IQ2_M.gguf) | i1-IQ2_M | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.8 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-Q2_K.gguf) | i1-Q2_K | 1.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.2 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-IQ3_S.gguf) | i1-IQ3_S | 2.2 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-IQ3_M.gguf) | i1-IQ3_M | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.3 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-Q4_0.gguf) | i1-Q4_0 | 2.7 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.7 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-Q4_1.gguf) | i1-Q4_1 | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-i1-GGUF/resolve/main/Qwen3-4B-Exp2.i1-Q6_K.gguf) | i1-Q6_K | 3.7 | 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. + +