commit b7813102a0798964ba2bceda11d908996c8d89e4 Author: ModelHub XC Date: Mon May 25 03:36:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a15c812 --- /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 +KONI-Llama3.1-8B-R-20250831.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KONI-Llama3.1-8B-R-20250831.i1-IQ1_M.gguf b/KONI-Llama3.1-8B-R-20250831.i1-IQ1_M.gguf new file mode 100644 index 0000000..2669711 --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d269898b3de0aa2650d0384631ba598ffd2ec9a58c3fbb93e8961f98812dfc6 +size 2161978336 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-IQ1_S.gguf b/KONI-Llama3.1-8B-R-20250831.i1-IQ1_S.gguf new file mode 100644 index 0000000..4f0a128 --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00cc43fed6a1d3f46d34306c31c916d779e7a2480d144cac6272023a57f5794b +size 2019634144 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-IQ2_M.gguf b/KONI-Llama3.1-8B-R-20250831.i1-IQ2_M.gguf new file mode 100644 index 0000000..74a239d --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6e1ac399b876aa80f3c1eaf5d4271d8c45e5fc62bf449ef648e05e16adfbb13 +size 2948287456 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-IQ2_S.gguf b/KONI-Llama3.1-8B-R-20250831.i1-IQ2_S.gguf new file mode 100644 index 0000000..e7033cc --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:731c2d5064236dc7ffe9c2ab1a74aab4dcdbd027fa2a00a0cf76aab5a21f676a +size 2758495200 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-IQ2_XS.gguf b/KONI-Llama3.1-8B-R-20250831.i1-IQ2_XS.gguf new file mode 100644 index 0000000..3b88862 --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f53b1b67d5ab2d01ac6be14ee5d14da1d1794061028766cd38e4bc0c4d036cfa +size 2605788128 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-IQ2_XXS.gguf b/KONI-Llama3.1-8B-R-20250831.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..a8797ce --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c6836780190f3b177b6733b3c66a699d993aaecf3a9970b731d28c06b991fac +size 2399218656 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-IQ3_M.gguf b/KONI-Llama3.1-8B-R-20250831.i1-IQ3_M.gguf new file mode 100644 index 0000000..5af14f0 --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79e82747b16cf11983b1605ceebdbcb1d02fce4cea94d46e2365123e7a09b12a +size 3784829920 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-IQ3_S.gguf b/KONI-Llama3.1-8B-R-20250831.i1-IQ3_S.gguf new file mode 100644 index 0000000..7b7929c --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1ab7edb8680738c56cfdc9331ef160e3df5fb74038901e2dabdc0f89d027e4b +size 3682331616 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-IQ3_XS.gguf b/KONI-Llama3.1-8B-R-20250831.i1-IQ3_XS.gguf new file mode 100644 index 0000000..0c7fafd --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fd52a0e5e4ccc425b326704218591e05a820532782f60f08e24260b2f8bd809 +size 3518753760 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-IQ3_XXS.gguf b/KONI-Llama3.1-8B-R-20250831.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..177582a --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad35feaf3fdf2d3282bab813fa82755e48ae471dc2f538833bb1c4e8616736f4 +size 3274918880 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-IQ4_NL.gguf b/KONI-Llama3.1-8B-R-20250831.i1-IQ4_NL.gguf new file mode 100644 index 0000000..73e5c77 --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ff66cc5e20820e5532b2bac4383972369cf25e2bced3e8948e7aa6f5043c75b +size 4677995488 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-IQ4_XS.gguf b/KONI-Llama3.1-8B-R-20250831.i1-IQ4_XS.gguf new file mode 100644 index 0000000..b1977f8 --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:208833cc0a8dd102d981e2719601cfb70a6c6cbad75d0f4e8488b45d229a8541 +size 4447669216 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-Q2_K.gguf b/KONI-Llama3.1-8B-R-20250831.i1-Q2_K.gguf new file mode 100644 index 0000000..fb2dcf2 --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0629aa449494b5d1559b6b4788530e09ebe45e02974dfd56c1c840f411efac78 +size 3179138016 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-Q2_K_S.gguf b/KONI-Llama3.1-8B-R-20250831.i1-Q2_K_S.gguf new file mode 100644 index 0000000..66ef9b1 --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f73b113970e0623ecffc3ed5e0c5d49cc3aaa9acf7194dee515f92c71730245 +size 2988821472 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-Q3_K_L.gguf b/KONI-Llama3.1-8B-R-20250831.i1-Q3_K_L.gguf new file mode 100644 index 0000000..de454ef --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:370f36f50260a9e290a6b287d5901a3762c272c54bb7f7f9a7d075e2073d6987 +size 4321962976 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-Q3_K_M.gguf b/KONI-Llama3.1-8B-R-20250831.i1-Q3_K_M.gguf new file mode 100644 index 0000000..8065008 --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cecb800efcb56264a98b8966c88c77417e7e33805f0234c4cc7e5da9ceec238d +size 4018924512 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-Q3_K_S.gguf b/KONI-Llama3.1-8B-R-20250831.i1-Q3_K_S.gguf new file mode 100644 index 0000000..561f239 --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c61c68dcbba112d28c1ce810cd468a3fd7c84fe81426d06d07b9999788f389b +size 3664505824 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-Q4_0.gguf b/KONI-Llama3.1-8B-R-20250831.i1-Q4_0.gguf new file mode 100644 index 0000000..0e83af9 --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:968004c67f5a1a5b02750e77b58bf0ae5c236b7e826d38f64a5972d2320aa9cd +size 4675898336 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-Q4_1.gguf b/KONI-Llama3.1-8B-R-20250831.i1-Q4_1.gguf new file mode 100644 index 0000000..031b896 --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab8bf443f24b3df72cb3f17cf1e104a88b0e84188d5061d3fffb88f5d9009647 +size 5130259424 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-Q4_K_M.gguf b/KONI-Llama3.1-8B-R-20250831.i1-Q4_K_M.gguf new file mode 100644 index 0000000..3a74f34 --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66f95d453b53fad2021a6e626f5f0f0bd874b560554899cd2d2b7050d0d9e3fb +size 4920740832 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-Q4_K_S.gguf b/KONI-Llama3.1-8B-R-20250831.i1-Q4_K_S.gguf new file mode 100644 index 0000000..fe71694 --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:440e91e854f94797ba90abe8964c6137863b0a7aad75707842147ae2882240db +size 4692675552 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-Q5_K_M.gguf b/KONI-Llama3.1-8B-R-20250831.i1-Q5_K_M.gguf new file mode 100644 index 0000000..97dcf62 --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:347d34176e22658a697cf3717504df0c7701a4272afb963ef43ab1c703c32bd1 +size 5732994016 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-Q5_K_S.gguf b/KONI-Llama3.1-8B-R-20250831.i1-Q5_K_S.gguf new file mode 100644 index 0000000..1e3c9bc --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4aa0a553439ece8edc9c5b7d53ba97869fae5344b333e96279beeab31efd2177 +size 5599300576 diff --git a/KONI-Llama3.1-8B-R-20250831.i1-Q6_K.gguf b/KONI-Llama3.1-8B-R-20250831.i1-Q6_K.gguf new file mode 100644 index 0000000..1123f47 --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be5535ed3afa9f24a6e27baa3a1110fd9feb978cded7ada1365478851240d13a +size 6596013024 diff --git a/KONI-Llama3.1-8B-R-20250831.imatrix.gguf b/KONI-Llama3.1-8B-R-20250831.imatrix.gguf new file mode 100644 index 0000000..0ce2c5a --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5eb7f882ddf732ac3180892487b91c9f5abb8b6beb04f2d09377f47d828f3b9 +size 5015200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f431849 --- /dev/null +++ b/README.md @@ -0,0 +1,93 @@ +--- +base_model: KISTI-KONI/KONI-Llama3.1-8B-R-20250831 +language: +- ko +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation +- pytorch +- llama3.1 +- KISTI +- KONI +- 8b +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/KISTI-KONI/KONI-Llama3.1-8B-R-20250831 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#KONI-Llama3.1-8B-R-20250831-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-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/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-i1-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.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. + +