commit ff527f21771d1dc1bc1c7853f49d2780da4272c9 Author: ModelHub XC Date: Sun May 10 06:11:57 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..87530fb --- /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-decensored-instruct.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4b-decensored-instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4b-decensored-instruct.i1-IQ1_M.gguf b/Qwen3-4b-decensored-instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..6ff9c96 --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53d6aa4bc9ebc1df97967416c911481c36758f2464069e057e5d0c1d67c794c7 +size 1127016896 diff --git a/Qwen3-4b-decensored-instruct.i1-IQ1_S.gguf b/Qwen3-4b-decensored-instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..ce1e2bd --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53242065f05a872c5cc3e8256dd029d5e27417469c6f223e197ca39c60030c32 +size 1055254976 diff --git a/Qwen3-4b-decensored-instruct.i1-IQ2_M.gguf b/Qwen3-4b-decensored-instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..58e4f1f --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25404f3c97f6f1767e32ddf74ed9fe769c7bcdee3a8b228c2c52e92a55c96146 +size 1512982976 diff --git a/Qwen3-4b-decensored-instruct.i1-IQ2_S.gguf b/Qwen3-4b-decensored-instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..a3bf7e9 --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:008d4d5a0ada97b160896f2da88e328af6d1e91196a721d2b4e786a9fb6f68c9 +size 1417300416 diff --git a/Qwen3-4b-decensored-instruct.i1-IQ2_XS.gguf b/Qwen3-4b-decensored-instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..2c77672 --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98addf15cbe5a405ef0bba3415bff011fd5923332921c9f9ffe6d87b0f62ab61 +size 1354099136 diff --git a/Qwen3-4b-decensored-instruct.i1-IQ2_XXS.gguf b/Qwen3-4b-decensored-instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..01f8144 --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea520af371717b01bd6c0bc2575df3cbc9132c76766cc6e13420a76ecf3c7af4 +size 1246620096 diff --git a/Qwen3-4b-decensored-instruct.i1-IQ3_M.gguf b/Qwen3-4b-decensored-instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..7e9e03d --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:600aa1bda9efa0e20f60298717c8b36c60ce7bf6eb0ec7b4a895cd60be8b07c5 +size 1962895296 diff --git a/Qwen3-4b-decensored-instruct.i1-IQ3_S.gguf b/Qwen3-4b-decensored-instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..693236b --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cea713fac65ab252551847f4b06c9f0935d5d9471ee39bdfddbe2187a331d78 +size 1899530176 diff --git a/Qwen3-4b-decensored-instruct.i1-IQ3_XS.gguf b/Qwen3-4b-decensored-instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..6d6048b --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32d47ed1c1ef8cd954ee7c9688a7a251c29fa91ff972117bfb3b751f611e8228 +size 1814374336 diff --git a/Qwen3-4b-decensored-instruct.i1-IQ3_XXS.gguf b/Qwen3-4b-decensored-instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..c00955a --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:968bcef4450ecba7ca64bb78f108afd619fe601b29f3a855f42b70571a81182f +size 1670187456 diff --git a/Qwen3-4b-decensored-instruct.i1-IQ4_NL.gguf b/Qwen3-4b-decensored-instruct.i1-IQ4_NL.gguf new file mode 100644 index 0000000..784f8d2 --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53601f4cec2494ef2642ee3b072c46ffd16d818937d4cd4b921c20153ab73138 +size 2381342656 diff --git a/Qwen3-4b-decensored-instruct.i1-IQ4_XS.gguf b/Qwen3-4b-decensored-instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..a20a704 --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:084fa950e4aeab67b716815d82a88ade124849f10acaa5436a561b6c711547f1 +size 2270750656 diff --git a/Qwen3-4b-decensored-instruct.i1-Q2_K.gguf b/Qwen3-4b-decensored-instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..4a9c249 --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ea8d541e1de846e4f9ea26c0477557ffd6b00a70df5a1362668fe4415d78331 +size 1669498816 diff --git a/Qwen3-4b-decensored-instruct.i1-Q2_K_S.gguf b/Qwen3-4b-decensored-instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..dbd3f50 --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f205cce2310ff65bffbf6b5957df438c0d5ad3c8f36ae177f473666782e243a +size 1563453376 diff --git a/Qwen3-4b-decensored-instruct.i1-Q3_K_L.gguf b/Qwen3-4b-decensored-instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..933f649 --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3acdae1e3696b0abec1edfccfd707a95879844f4dbf506c1df2f01cd7922d13e +size 2239784896 diff --git a/Qwen3-4b-decensored-instruct.i1-Q3_K_M.gguf b/Qwen3-4b-decensored-instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..d440fc9 --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bffbe27d85ae329b40f90fc1dcc920f3e1cb75b496a378ad2175c461a66e7d3f +size 2075617216 diff --git a/Qwen3-4b-decensored-instruct.i1-Q3_K_S.gguf b/Qwen3-4b-decensored-instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..d2f9608 --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f69d114fe3f45d44dbe57fd96bc500399aa93545a0ec8910777e1f18d1b941bc +size 1886996416 diff --git a/Qwen3-4b-decensored-instruct.i1-Q4_0.gguf b/Qwen3-4b-decensored-instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..02c7d72 --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42189d8a04bbfe9c26bd154bc2fe20f8d182d1a5c3b032ffc382d3b7c450bbce +size 2375772096 diff --git a/Qwen3-4b-decensored-instruct.i1-Q4_1.gguf b/Qwen3-4b-decensored-instruct.i1-Q4_1.gguf new file mode 100644 index 0000000..6ded47a --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a714d62512fa8b3e0ccbcdbbd402be0993bd633c03b19c6f1a41589a8dc0130 +size 2596628416 diff --git a/Qwen3-4b-decensored-instruct.i1-Q4_K_M.gguf b/Qwen3-4b-decensored-instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..eaba609 --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84a517032c0bbc6ee8dd4521f14559eb5e0c13882094ed74ab0c1d5b20039ddc +size 2497279936 diff --git a/Qwen3-4b-decensored-instruct.i1-Q4_K_S.gguf b/Qwen3-4b-decensored-instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..d5b1bfa --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abc8ffc95bfec1e233e096e50a7baf07a95898b318435701d7cca61622130631 +size 2383308736 diff --git a/Qwen3-4b-decensored-instruct.i1-Q5_K_M.gguf b/Qwen3-4b-decensored-instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..4afc2be --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dc446954e28e1eff569090deec8ae69328b046da4ee790147454db69b46bb00 +size 2889512896 diff --git a/Qwen3-4b-decensored-instruct.i1-Q5_K_S.gguf b/Qwen3-4b-decensored-instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..93351d3 --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:feb75a83a9b3899cfdab816ea32690407405155338f88f5de95bf6124998b004 +size 2823710656 diff --git a/Qwen3-4b-decensored-instruct.i1-Q6_K.gguf b/Qwen3-4b-decensored-instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..e8f372c --- /dev/null +++ b/Qwen3-4b-decensored-instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a478e30b56b478d23529c02cad832da8d28e962bbd052e8ff07f058103f5fef +size 3306260416 diff --git a/Qwen3-4b-decensored-instruct.imatrix.gguf b/Qwen3-4b-decensored-instruct.imatrix.gguf new file mode 100644 index 0000000..779102a --- /dev/null +++ b/Qwen3-4b-decensored-instruct.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c41f92870d9c2c5104231321e2d5d574ce19e2e4ea0c9d83925c079db81ee05c +size 3872640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4ce7e53 --- /dev/null +++ b/README.md @@ -0,0 +1,91 @@ +--- +base_model: laurentiurad/Qwen3-4b-decensored-instruct +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507/blob/main/LICENSE +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- heretic +- uncensored +- decensored +- abliterated +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/laurentiurad/Qwen3-4b-decensored-instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4b-decensored-instruct-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-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-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4b-decensored-instruct-i1-GGUF/resolve/main/Qwen3-4b-decensored-instruct.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. + +