commit 8c65b758b6e188c84e47550002127a3fd38f3918 Author: ModelHub XC Date: Mon May 25 04:24:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-abliterated-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..64ae0f3 --- /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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-abliterated.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-abliterated.i1-IQ1_M.gguf b/Qwen3-4B-abliterated.i1-IQ1_M.gguf new file mode 100644 index 0000000..3ddb43a --- /dev/null +++ b/Qwen3-4B-abliterated.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65467dd1239567cf2d0dd55eca8140c61dcdf970c885675386ae533059e77265 +size 1127017920 diff --git a/Qwen3-4B-abliterated.i1-IQ1_S.gguf b/Qwen3-4B-abliterated.i1-IQ1_S.gguf new file mode 100644 index 0000000..4703cce --- /dev/null +++ b/Qwen3-4B-abliterated.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2231986bbb8528d046c6ea855f58d5646a04339acc6c8917972733d9bd5ce696 +size 1055256000 diff --git a/Qwen3-4B-abliterated.i1-IQ2_M.gguf b/Qwen3-4B-abliterated.i1-IQ2_M.gguf new file mode 100644 index 0000000..9998a0d --- /dev/null +++ b/Qwen3-4B-abliterated.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67dcdc2527bff946bf422402f3fecf8e52eb6af084d161e36792c6be2f24efe2 +size 1512984000 diff --git a/Qwen3-4B-abliterated.i1-IQ2_S.gguf b/Qwen3-4B-abliterated.i1-IQ2_S.gguf new file mode 100644 index 0000000..f7044a6 --- /dev/null +++ b/Qwen3-4B-abliterated.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39e8ea257d6131305a5540312d06cadb63eab099832a31c1068d8153d31b0d5f +size 1417301440 diff --git a/Qwen3-4B-abliterated.i1-IQ2_XS.gguf b/Qwen3-4B-abliterated.i1-IQ2_XS.gguf new file mode 100644 index 0000000..867d12c --- /dev/null +++ b/Qwen3-4B-abliterated.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3255508fca3be87c6d1e2db31c1583bd1ce8fd78e4189ea3681360cdf5b3532 +size 1354100160 diff --git a/Qwen3-4B-abliterated.i1-IQ2_XXS.gguf b/Qwen3-4B-abliterated.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..4ff81f1 --- /dev/null +++ b/Qwen3-4B-abliterated.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d17e808c3247ed0092fa2bcd2fd4970670394e5410d016a6f4144143c23dae7 +size 1246621120 diff --git a/Qwen3-4B-abliterated.i1-IQ3_M.gguf b/Qwen3-4B-abliterated.i1-IQ3_M.gguf new file mode 100644 index 0000000..dccb71c --- /dev/null +++ b/Qwen3-4B-abliterated.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c62da9bc8e31c13188d86c10b65e8fe0fd3e1c4d26f9fc143202a4cad187e6d9 +size 1962896320 diff --git a/Qwen3-4B-abliterated.i1-IQ3_S.gguf b/Qwen3-4B-abliterated.i1-IQ3_S.gguf new file mode 100644 index 0000000..8e3a447 --- /dev/null +++ b/Qwen3-4B-abliterated.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0c786ee498b7d4115b6e835cce81608353a2b833860450cd61a780ada5ac38d +size 1899531200 diff --git a/Qwen3-4B-abliterated.i1-IQ3_XS.gguf b/Qwen3-4B-abliterated.i1-IQ3_XS.gguf new file mode 100644 index 0000000..d4433eb --- /dev/null +++ b/Qwen3-4B-abliterated.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e664d32146d478315a9053ba6282934c195564fee752eeaab43d9deb8a587ea +size 1814375360 diff --git a/Qwen3-4B-abliterated.i1-IQ3_XXS.gguf b/Qwen3-4B-abliterated.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..cf4b79d --- /dev/null +++ b/Qwen3-4B-abliterated.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d5a07fc67378927852ec697102e57ef5c752e9752ce7ecb849dcb8d0780003d +size 1670188480 diff --git a/Qwen3-4B-abliterated.i1-IQ4_NL.gguf b/Qwen3-4B-abliterated.i1-IQ4_NL.gguf new file mode 100644 index 0000000..3a68ff2 --- /dev/null +++ b/Qwen3-4B-abliterated.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3223ea39a61c5de381ab32e5f8949cd36ae608f877cdbfc353fcb992ff15f273 +size 2381343680 diff --git a/Qwen3-4B-abliterated.i1-IQ4_XS.gguf b/Qwen3-4B-abliterated.i1-IQ4_XS.gguf new file mode 100644 index 0000000..6cc405d --- /dev/null +++ b/Qwen3-4B-abliterated.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a563cbaa10b835e3828cd8a36dcd31f68146576d9a49496cbe1b0251a1dfbdc9 +size 2270751680 diff --git a/Qwen3-4B-abliterated.i1-Q2_K.gguf b/Qwen3-4B-abliterated.i1-Q2_K.gguf new file mode 100644 index 0000000..1a15c0d --- /dev/null +++ b/Qwen3-4B-abliterated.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1df3017d572726fe82d5271f2ef14d95f16fc86559395e744970b9f6d4335547 +size 1669499840 diff --git a/Qwen3-4B-abliterated.i1-Q2_K_S.gguf b/Qwen3-4B-abliterated.i1-Q2_K_S.gguf new file mode 100644 index 0000000..3abef57 --- /dev/null +++ b/Qwen3-4B-abliterated.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cf6e7af4101f8574160041359c74c1f54b77fb46897aa5a03d38d6d37a65ce0 +size 1563454400 diff --git a/Qwen3-4B-abliterated.i1-Q3_K_L.gguf b/Qwen3-4B-abliterated.i1-Q3_K_L.gguf new file mode 100644 index 0000000..1042c93 --- /dev/null +++ b/Qwen3-4B-abliterated.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:111316e94c8dbfb92307fa30c2ef109eca35c83c9e74af3f50c65c0e796efd4b +size 2239785920 diff --git a/Qwen3-4B-abliterated.i1-Q3_K_M.gguf b/Qwen3-4B-abliterated.i1-Q3_K_M.gguf new file mode 100644 index 0000000..147d69e --- /dev/null +++ b/Qwen3-4B-abliterated.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ef2244a76e2ca4a5a6f530d04c19b1a1898e042d76124167aeb7facd36995c4 +size 2075618240 diff --git a/Qwen3-4B-abliterated.i1-Q3_K_S.gguf b/Qwen3-4B-abliterated.i1-Q3_K_S.gguf new file mode 100644 index 0000000..9414b15 --- /dev/null +++ b/Qwen3-4B-abliterated.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8f924c99746f1bb2637eecfbb723ba8d9d5ab19246123b603727d461f88c309 +size 1886997440 diff --git a/Qwen3-4B-abliterated.i1-Q4_0.gguf b/Qwen3-4B-abliterated.i1-Q4_0.gguf new file mode 100644 index 0000000..a7eb25e --- /dev/null +++ b/Qwen3-4B-abliterated.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4681693a0c8f806ece88d280eb8b080b7dc9f56622b2a2a70fcdfbad54facc2 +size 2375773120 diff --git a/Qwen3-4B-abliterated.i1-Q4_1.gguf b/Qwen3-4B-abliterated.i1-Q4_1.gguf new file mode 100644 index 0000000..8108b75 --- /dev/null +++ b/Qwen3-4B-abliterated.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2048ba1b7c4a98eea876290f9150624ad5b88dbef3517f9f95d8ae77cd52402 +size 2596629440 diff --git a/Qwen3-4B-abliterated.i1-Q4_K_M.gguf b/Qwen3-4B-abliterated.i1-Q4_K_M.gguf new file mode 100644 index 0000000..bb26480 --- /dev/null +++ b/Qwen3-4B-abliterated.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73fc03801e137b7145680f4b243e7326a41874a53519af921f7c84eb649bd801 +size 2497280960 diff --git a/Qwen3-4B-abliterated.i1-Q4_K_S.gguf b/Qwen3-4B-abliterated.i1-Q4_K_S.gguf new file mode 100644 index 0000000..d5d3e0a --- /dev/null +++ b/Qwen3-4B-abliterated.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:582ad96344d67e77a889791393e347e8ec14174811889c404d0cd9fb61d367b2 +size 2383309760 diff --git a/Qwen3-4B-abliterated.i1-Q5_K_M.gguf b/Qwen3-4B-abliterated.i1-Q5_K_M.gguf new file mode 100644 index 0000000..3f02dd7 --- /dev/null +++ b/Qwen3-4B-abliterated.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4aba52505c112ca1c5024ac871466d42477a1474e7a7e890faf130f001d5fff3 +size 2889513920 diff --git a/Qwen3-4B-abliterated.i1-Q5_K_S.gguf b/Qwen3-4B-abliterated.i1-Q5_K_S.gguf new file mode 100644 index 0000000..e235783 --- /dev/null +++ b/Qwen3-4B-abliterated.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:509ff6c0ecbbe5bbed38935182cfa40796dcd33283daa09c15185b7ab06651bb +size 2823711680 diff --git a/Qwen3-4B-abliterated.i1-Q6_K.gguf b/Qwen3-4B-abliterated.i1-Q6_K.gguf new file mode 100644 index 0000000..6720acc --- /dev/null +++ b/Qwen3-4B-abliterated.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc2a4c7c81e964d818b9bc18e860b8c997232c3e7ba26bed9887c1758ef5e70a +size 3306261440 diff --git a/README.md b/README.md new file mode 100644 index 0000000..aa5cb5d --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: mlabonne/Qwen3-4B-abliterated +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen3-0.6B/blob/main/LICENSE +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- abliteration +- abliterated +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/mlabonne/Qwen3-4B-abliterated + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-abliterated-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-4B-abliterated-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-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-abliterated-i1-GGUF/resolve/main/Qwen3-4B-abliterated.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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..266b08d --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a87f720681053611fee091f9957ebd4fa9a5eaf6f1d42b3db96d79da451bdc5 +size 3842209