commit f39befeb882f5df18cfb3058007bbf31a03676ce Author: ModelHub XC Date: Tue May 19 04:20:00 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d683981 --- /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 +Llama-3.3-8B-Instruct-128K_Abliterated.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ1_M.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ1_M.gguf new file mode 100644 index 0000000..bf5d283 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01f8ca31357200931557d56b4e6b721aa86b1900755892d2a4952e7e8a1afcca +size 2161977664 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ1_S.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ1_S.gguf new file mode 100644 index 0000000..6a55cba --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0daff079e12a037fa3d34e712ed474965acb44ccec51a8baadafb1d981ac6206 +size 2019633472 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ2_M.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ2_M.gguf new file mode 100644 index 0000000..eab0471 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a08a6df2897ec4586f323b8dbe936285652902fa7c2315df88120e9f50fdd75 +size 2948286784 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ2_S.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ2_S.gguf new file mode 100644 index 0000000..c920714 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62dfaf8ba5977f9dd2387b63cb3d91824797360e9430278be82ce841af9e5423 +size 2758494528 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ2_XS.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ2_XS.gguf new file mode 100644 index 0000000..11b9eb6 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:277f7f206443cdd393fec4a857ff83aac865eb58be6a3b02e45663d49de06e4c +size 2605787456 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ2_XXS.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..babe840 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abe74a6f3e5b0b320bff99e48a07913e539b155414d846329b60ff5eed40b2b5 +size 2399217984 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ3_M.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ3_M.gguf new file mode 100644 index 0000000..972aaf3 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca33b4bd6445c38bd6de6465cd09f11de7f2bdd84aae68016c11428ab7860499 +size 3784829248 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ3_S.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ3_S.gguf new file mode 100644 index 0000000..7a7b555 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09d6b778a5e409e1af5a8d111dd6e1497ff0cdc399576af2499c61b5318d288b +size 3682330944 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ3_XS.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ3_XS.gguf new file mode 100644 index 0000000..2dfba93 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4201ee49a3c10ad04051698f17b95cbac5c8e7cc73746700aa92a3d2b8689599 +size 3518753088 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ3_XXS.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..0346b2b --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74102c6035b94148be02329704f8ea0b8c0359138bc615f3b57ae50716b3af29 +size 3274918208 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ4_NL.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ4_NL.gguf new file mode 100644 index 0000000..a66899c --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6708043774bd5dbaa938016e18867a442ecd38d25b803500148c8217f47ae1ba +size 4677994816 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ4_XS.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ4_XS.gguf new file mode 100644 index 0000000..41b0b61 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3e7339788fd63cf9504ccca1e6af2cbb97649a615476e8449d99228bdce9c4a +size 4447668544 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q2_K.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q2_K.gguf new file mode 100644 index 0000000..47c6e52 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f59e1571c70f0af2e3b2937f6b39cfc725492b26bd5ac827879f5120141d2aa3 +size 3179137344 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q2_K_S.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q2_K_S.gguf new file mode 100644 index 0000000..8e26eca --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e15303325efc8cb67a1a8ee8b84c4bfa37170e2907e84dcf8cc18e4d08211b8 +size 2988820800 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q3_K_L.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q3_K_L.gguf new file mode 100644 index 0000000..a260ce9 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e72e000e20d775d1e971aa9d7f1fcb99c136fdbf28140f40d4748f576809fabb +size 4321962304 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q3_K_M.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q3_K_M.gguf new file mode 100644 index 0000000..484812a --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62f613338ab17dc93db9328f6ca574761c760812a501a5d4fc8dfc890cb73976 +size 4018923840 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q3_K_S.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q3_K_S.gguf new file mode 100644 index 0000000..03bb24d --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:960af11236dbc861daabdf9ed113e16b2a62cb01e726c8b9cc910d08b8e61d02 +size 3664505152 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q4_0.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q4_0.gguf new file mode 100644 index 0000000..0ac9577 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50c91122b4e54792f3d090dfc73f57377c9af1145fcfb70adc16e99c03dbdcc8 +size 4675897664 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q4_1.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q4_1.gguf new file mode 100644 index 0000000..8ee65ed --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaf36d1a75593690995582a25e6cfbd1a92789d9d6f2ca41f5f4a9598d587fb1 +size 5130258752 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q4_K_M.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q4_K_M.gguf new file mode 100644 index 0000000..f37c0a9 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30f1cd87397ec2a24b3b41cc172d86114874d9c4e76148640de945238856aacf +size 4920740160 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q4_K_S.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q4_K_S.gguf new file mode 100644 index 0000000..220ee99 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:785dba5e01a79d8cc1567067345d031f07d413c8fcaa728a5b30834b12c5a1a9 +size 4692674880 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q5_K_M.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q5_K_M.gguf new file mode 100644 index 0000000..66982c2 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c7d683a400fb35f08b8b077bf687510d4fd65c951d8078d634d3fd3bf30ca0a +size 5732993344 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q5_K_S.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q5_K_S.gguf new file mode 100644 index 0000000..6d80e09 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35f563c443d412687a32cc7d6cc55acddcd2079467a8db08c49508c303c84672 +size 5599299904 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q6_K.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q6_K.gguf new file mode 100644 index 0000000..2441f32 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:461003816225b82e16ffb6bf27d8590447d68d01ef84a387fd1e298414842510 +size 6596012352 diff --git a/Llama-3.3-8B-Instruct-128K_Abliterated.imatrix.gguf b/Llama-3.3-8B-Instruct-128K_Abliterated.imatrix.gguf new file mode 100644 index 0000000..ce87287 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K_Abliterated.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6a3d172453d41c9bf5f868525ec4b768abfa81701fb45e647328207a575beae +size 5015200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c5f083a --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: SicariusSicariiStuff/Llama-3.3-8B-Instruct-128K_Abliterated +language: +- en +library_name: transformers +license: llama3.3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/SicariusSicariiStuff/Llama-3.3-8B-Instruct-128K_Abliterated + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_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/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K_Abliterated-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K_Abliterated.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | 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. + +