commit b8c02ba105ef7e5b3a59b2956d7ba13a0359a6d5 Author: ModelHub XC Date: Sat Sep 26 01:09:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ABForge-Qwen3-8B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3aae384 --- /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 +ABForge-Qwen3-8B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +ABForge-Qwen3-8B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ABForge-Qwen3-8B.i1-IQ1_M.gguf b/ABForge-Qwen3-8B.i1-IQ1_M.gguf new file mode 100644 index 0000000..3e23b65 --- /dev/null +++ b/ABForge-Qwen3-8B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e009f580230272544a4324cf106b0b61e340d0c1c229d31c0d9c9e7488582ab4 +size 2256148448 diff --git a/ABForge-Qwen3-8B.i1-IQ1_S.gguf b/ABForge-Qwen3-8B.i1-IQ1_S.gguf new file mode 100644 index 0000000..af31263 --- /dev/null +++ b/ABForge-Qwen3-8B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b202c04fb19cc53e2c593ab7c2397162085bababb8bb3878fda440f0f5cfb452 +size 2115770336 diff --git a/ABForge-Qwen3-8B.i1-IQ2_M.gguf b/ABForge-Qwen3-8B.i1-IQ2_M.gguf new file mode 100644 index 0000000..184b655 --- /dev/null +++ b/ABForge-Qwen3-8B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12917cf828251cb404319d2967048cdc2bd65a4c2bfc86780454c31980f06d70 +size 3051915232 diff --git a/ABForge-Qwen3-8B.i1-IQ2_S.gguf b/ABForge-Qwen3-8B.i1-IQ2_S.gguf new file mode 100644 index 0000000..398fc4a --- /dev/null +++ b/ABForge-Qwen3-8B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be5a991e16104f952dc79c2828f19c7d538ae0f2cf6644edad0defcc6a3bc358 +size 2864744416 diff --git a/ABForge-Qwen3-8B.i1-IQ2_XS.gguf b/ABForge-Qwen3-8B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..ee32663 --- /dev/null +++ b/ABForge-Qwen3-8B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9e28b289a5e9b89fcd255daba3d2080ea766fa0947f22d0aa49d1d8357cd51c +size 2696157152 diff --git a/ABForge-Qwen3-8B.i1-IQ2_XXS.gguf b/ABForge-Qwen3-8B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..543c236 --- /dev/null +++ b/ABForge-Qwen3-8B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1512ebd51ca3f2377c64a9338e7a05f7ca974b3b14fc124ed833150c8d9d5b11 +size 2490111968 diff --git a/ABForge-Qwen3-8B.i1-IQ3_M.gguf b/ABForge-Qwen3-8B.i1-IQ3_M.gguf new file mode 100644 index 0000000..08c1a4a --- /dev/null +++ b/ABForge-Qwen3-8B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03719b92f1afc6b9096bd1b9259a254af2174fc1529c4f743f7fc3b8303c7158 +size 3896621024 diff --git a/ABForge-Qwen3-8B.i1-IQ3_S.gguf b/ABForge-Qwen3-8B.i1-IQ3_S.gguf new file mode 100644 index 0000000..84dfada --- /dev/null +++ b/ABForge-Qwen3-8B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85a5296888eab207d5da62d93c57841d3101a8db2202fe2f12fcc8f990f90b42 +size 3789666272 diff --git a/ABForge-Qwen3-8B.i1-IQ3_XS.gguf b/ABForge-Qwen3-8B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..828199c --- /dev/null +++ b/ABForge-Qwen3-8B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe002457b5a73028aa6be42a6b262de7a15e25215c47eaffb08141c7ee0a3862 +size 3626874848 diff --git a/ABForge-Qwen3-8B.i1-IQ3_XXS.gguf b/ABForge-Qwen3-8B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..d92039e --- /dev/null +++ b/ABForge-Qwen3-8B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:560663332ebbdd892d96658cfad020a946354101375b9489a34173374482a0c5 +size 3369633760 diff --git a/ABForge-Qwen3-8B.i1-IQ4_NL.gguf b/ABForge-Qwen3-8B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..66e806d --- /dev/null +++ b/ABForge-Qwen3-8B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:136a0f2c7958d06e723e6aff5b17a024c208ed989f12b3843015af2f3b2490a8 +size 4793624544 diff --git a/ABForge-Qwen3-8B.i1-IQ4_XS.gguf b/ABForge-Qwen3-8B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..1a66155 --- /dev/null +++ b/ABForge-Qwen3-8B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9ac76dcfb34e9d739bd5343fa695391d15c9e347dfb4e08a2dd2829184b4f35 +size 4561840096 diff --git a/ABForge-Qwen3-8B.i1-Q2_K.gguf b/ABForge-Qwen3-8B.i1-Q2_K.gguf new file mode 100644 index 0000000..202835b --- /dev/null +++ b/ABForge-Qwen3-8B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b8c704e6b49ec59cb276bf3ee9590ea828365b2193b58b661bf13ae2cd7c103 +size 3281733600 diff --git a/ABForge-Qwen3-8B.i1-Q2_K_S.gguf b/ABForge-Qwen3-8B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..285e631 --- /dev/null +++ b/ABForge-Qwen3-8B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55cccdbde526383c3b2c6326c67cb0921b30b4b00daffdffe94684e34389f089 +size 3083552736 diff --git a/ABForge-Qwen3-8B.i1-Q3_K_L.gguf b/ABForge-Qwen3-8B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..2add086 --- /dev/null +++ b/ABForge-Qwen3-8B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1db9818e225fe508318cee5b5319e4f6c02ff6f94f02b940b2622c0c9aab4e1f +size 4431394784 diff --git a/ABForge-Qwen3-8B.i1-Q3_K_M.gguf b/ABForge-Qwen3-8B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..88293c2 --- /dev/null +++ b/ABForge-Qwen3-8B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4775a02ca269f497a91f93954cc6993af97e0ade0af0fb80256b30810040f197 +size 4124162016 diff --git a/ABForge-Qwen3-8B.i1-Q3_K_S.gguf b/ABForge-Qwen3-8B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..0e31adc --- /dev/null +++ b/ABForge-Qwen3-8B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29c1ef351e23c97cea625620816c47b9b1fd015384cd756773da3b45b753f4e2 +size 3769612256 diff --git a/ABForge-Qwen3-8B.i1-Q4_0.gguf b/ABForge-Qwen3-8B.i1-Q4_0.gguf new file mode 100644 index 0000000..ea9c7b5 --- /dev/null +++ b/ABForge-Qwen3-8B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3a7a9abbc4a75d097144fb812465efc7ced5747d87a9707971768da0846ba01 +size 4787333088 diff --git a/ABForge-Qwen3-8B.i1-Q4_1.gguf b/ABForge-Qwen3-8B.i1-Q4_1.gguf new file mode 100644 index 0000000..2cde020 --- /dev/null +++ b/ABForge-Qwen3-8B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c123b17a5bf79ab1dbb7e4a6e58a46d620db0c0933f3aaf06950d066134ba8d +size 5247756256 diff --git a/ABForge-Qwen3-8B.i1-Q4_K_M.gguf b/ABForge-Qwen3-8B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..5f3ebfb --- /dev/null +++ b/ABForge-Qwen3-8B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c7391c4ed673bba412928f7d82716c347835ed60df3b6d04b274b50200f68a9 +size 5027784672 diff --git a/ABForge-Qwen3-8B.i1-Q4_K_S.gguf b/ABForge-Qwen3-8B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..3cf3a57 --- /dev/null +++ b/ABForge-Qwen3-8B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ef73dcf9547f404d1e3b4c26de94a43b1ca958e162b8c7b23717f543a294f11 +size 4802013152 diff --git a/ABForge-Qwen3-8B.i1-Q5_K_M.gguf b/ABForge-Qwen3-8B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..a178e67 --- /dev/null +++ b/ABForge-Qwen3-8B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdd80e88845a2d77189fd43b2e49b200292e0c88f5a5852b02ebb7c991c97b4f +size 5851113440 diff --git a/ABForge-Qwen3-8B.i1-Q5_K_S.gguf b/ABForge-Qwen3-8B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..f4eedfe --- /dev/null +++ b/ABForge-Qwen3-8B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25055ad4ea7c5dccf3485789f247f2a0484d77d57c2de567f769e9957544093e +size 5720762336 diff --git a/ABForge-Qwen3-8B.i1-Q6_K.gguf b/ABForge-Qwen3-8B.i1-Q6_K.gguf new file mode 100644 index 0000000..ddc0dde --- /dev/null +++ b/ABForge-Qwen3-8B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e70397ddde47517e313c49d9b33ad5beca665bf6a188c3ba4af355bb3a867ab5 +size 6725900256 diff --git a/ABForge-Qwen3-8B.imatrix.gguf b/ABForge-Qwen3-8B.imatrix.gguf new file mode 100644 index 0000000..6b6ced5 --- /dev/null +++ b/ABForge-Qwen3-8B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1008ffdb12c80baa738cd2041dea5f5432cd9c1ed0cc875cf6ebda4e38115e43 +size 5347200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dbb543b --- /dev/null +++ b/README.md @@ -0,0 +1,92 @@ +--- +base_model: SlowGuess/ABForge-Qwen3-8B +datasets: +- SlowGuess/abforge-data +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- ablation-study +- scientific-reasoning +- post-training +- qwen3 +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/SlowGuess/ABForge-Qwen3-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ABForge-Qwen3-8B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/ABForge-Qwen3-8B-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/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-IQ2_S.gguf) | i1-IQ2_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.2 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.9 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-IQ3_M.gguf) | i1-IQ3_M | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-Q4_0.gguf) | i1-Q4_0 | 4.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.9 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-Q4_1.gguf) | i1-Q4_1 | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/ABForge-Qwen3-8B-i1-GGUF/resolve/main/ABForge-Qwen3-8B.i1-Q6_K.gguf) | i1-Q6_K | 6.8 | 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. + +