commit 36acad08d7eb6ee76b678ad1fbb6452fa98863a1 Author: ModelHub XC Date: Mon May 25 19:33:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a03af72 --- /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 +Qwen3-0.6B-Code-Expert-abliterated.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert-abliterated.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ1_M.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ1_M.gguf new file mode 100644 index 0000000..7ac48a5 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c571f6806f787024d2917e12cdd608ea9c7fa6ac0d6226d25fc80d719d4d70a +size 216053568 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ1_S.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ1_S.gguf new file mode 100644 index 0000000..0477de1 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:398eef89a7b8955d2a2dc199ffff8c2a72bf068867bb2a4f545d7beabbe6bf5f +size 208017216 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ2_M.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ2_M.gguf new file mode 100644 index 0000000..2fa3900 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ae3436040de06cce359f64c39e1aa9fbd359b39668eefd2ba3e604fdb676d51 +size 264910656 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ2_S.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ2_S.gguf new file mode 100644 index 0000000..d6f2736 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72b82f2fab097a1aff74de2bad5ca6135c20581fc0c751f46829445c18045a5b +size 254195520 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ2_XS.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ2_XS.gguf new file mode 100644 index 0000000..0a06b92 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68d5e5ba73b7215e9d0cd287c695df90903379a46f69101040c719154ef02939 +size 241997632 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ2_XXS.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..8c0d503 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c23401ba21eca8131a5bbc1efaa9267734f7b6ccce891b736a50fa560491862d +size 229447488 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ3_M.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ3_M.gguf new file mode 100644 index 0000000..7869f80 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a3ed3be1484ac232b6d1ba920b56a2cf4930374bbd2211d087335376329582f +size 336028480 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ3_S.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ3_S.gguf new file mode 100644 index 0000000..973095e --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6629def08395b3a95f831ee834529e8b1c111cb508106ad2999151d53bfdbb0 +size 323076928 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ3_XS.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ3_XS.gguf new file mode 100644 index 0000000..ebc2c3e --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4a6cd858213cee405ca6c6c1d8f05a83ed94594a3968ed5ae691877216ee13e +size 312755008 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ3_XXS.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..0a68db7 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b332809ccb7af6db304991d686976eb684ce1c7bdd512746f03d7b39a074316 +size 279017280 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ4_NL.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ4_NL.gguf new file mode 100644 index 0000000..d8c1d40 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d19e662be2e6a02a4099276088b153fdb11a4bc4dceb120df66751cf927fe2a +size 381567808 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ4_XS.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ4_XS.gguf new file mode 100644 index 0000000..64323eb --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec934f6ff85299584c08efe8279971cabd94ce8a9c00acf20a2825930abe1062 +size 367805248 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-Q2_K.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q2_K.gguf new file mode 100644 index 0000000..b5cc5df --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63f80a6151ef691153e8c605092bbde9b7edaf0aa33e1f6e355c3be39848195f +size 296239936 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-Q2_K_S.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q2_K_S.gguf new file mode 100644 index 0000000..4986c6b --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0bde92a26986c26b244b0de202667fed5a438572a9773663a420e82cda04887 +size 280560448 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-Q3_K_L.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q3_K_L.gguf new file mode 100644 index 0000000..b4b8848 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e5ee066af8f44d1581a70f08426b6de8900c760586575e0d8a66bcc00edc40b +size 368493376 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-Q3_K_M.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q3_K_M.gguf new file mode 100644 index 0000000..7f4eab1 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeab182ce1e8cdd17859abd4abb05209ac5d0d35dd0065d1329a5b904db03d9c +size 347128640 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-Q3_K_S.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q3_K_S.gguf new file mode 100644 index 0000000..5b7cea5 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e073bdd81c582fc5e6fce8387b0742174207d86778dc6e0b58266be1d14e70f +size 323076928 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-Q4_0.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q4_0.gguf new file mode 100644 index 0000000..ad22b9c --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b32a588102c21472a2dada11e077ac67210f9aba0f9763cd0650d9978a293b9 +size 382157632 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-Q4_1.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q4_1.gguf new file mode 100644 index 0000000..354fad5 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c3c90923c3facd3ddf64a64ebabe084ae5fd93824666730c41113926f4426bd +size 409092928 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-Q4_K_M.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q4_K_M.gguf new file mode 100644 index 0000000..f69dba6 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7f77d8a84c0ab855b472f24559e2d41697ba9b907b8307d6514b4f5ad251a9a +size 396706624 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-Q4_K_S.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q4_K_S.gguf new file mode 100644 index 0000000..d580b5e --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd7258ab074ca7c60fada2ecd25841745232e4b08a1c503f3d189bee0ae6dd6e +size 383271744 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-Q5_K_M.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q5_K_M.gguf new file mode 100644 index 0000000..37923dd --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aab8691a7459dc961ac7d850b95e88adbd07c79338778c47dee5455c4d92536 +size 444416832 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-Q5_K_S.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q5_K_S.gguf new file mode 100644 index 0000000..5bf1fb5 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15228eb3c57bfd708138fad5296e05f22a34ad0aeb9f6e37a32ebbc93269c26a +size 436618048 diff --git a/Qwen3-0.6B-Code-Expert-abliterated.i1-Q6_K.gguf b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q6_K.gguf new file mode 100644 index 0000000..358c6a6 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert-abliterated.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:556eded9429c5b78b73bc217905e490295de5b24373c250a534580c8116e7f4e +size 495108928 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5f8a111 --- /dev/null +++ b/README.md @@ -0,0 +1,91 @@ +--- +base_model: lunahr/Qwen3-0.6B-Code-Expert-abliterated +datasets: +- nvidia/OpenCodeReasoning +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +- code +- reasoning +- abliterated +- baukit-abliterated +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/lunahr/Qwen3-0.6B-Code-Expert-abliterated + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-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/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ1_S.gguf) | i1-IQ1_S | 0.3 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ1_M.gguf) | i1-IQ1_M | 0.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ2_S.gguf) | i1-IQ2_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ2_M.gguf) | i1-IQ2_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-Q2_K.gguf) | i1-Q2_K | 0.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ3_S.gguf) | i1-IQ3_S | 0.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ3_M.gguf) | i1-IQ3_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-Q4_0.gguf) | i1-Q4_0 | 0.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-Q4_1.gguf) | i1-Q4_1 | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-abliterated-i1-GGUF/resolve/main/Qwen3-0.6B-Code-Expert-abliterated.i1-Q6_K.gguf) | i1-Q6_K | 0.6 | 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..43e0670 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8914547fc94526e9d0010c1a3ba25ab080d665ca91a3776e54496ea42b862ac5 +size 1153369