commit efa13e5450cea5ffdd7eba880fdde57f59962d4e Author: ModelHub XC Date: Sun Jun 28 13:55:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ea0d8a9 --- /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 +EXAONE-3.0-7.8B-Instruct-converted.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ1_M.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ1_M.gguf new file mode 100644 index 0000000..1bc7a9c --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f4b5cc5fb44408578af1eb3a6645d76b0a4c01ea61287cf9404976a40984141 +size 2050775168 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ1_S.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ1_S.gguf new file mode 100644 index 0000000..2290e97 --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d47dafdc78d40749cb7efb0966dc3e19f68bed135bf519582eebfa0e230b18f +size 1908430976 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ2_M.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ2_M.gguf new file mode 100644 index 0000000..ff7b6ca --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f50caa27fe5dcf008c10f8ab46a283110a61a6eef9a8839be5851abdde3304b +size 2826328192 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ2_S.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ2_S.gguf new file mode 100644 index 0000000..f285048 --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cb57eeb3705faa1fac24fb82f3b9d55541607a2669307d533a4f0fa7cb9a422 +size 2636535936 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ2_XS.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ2_XS.gguf new file mode 100644 index 0000000..f219e67 --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04a12a137614499eec18380c9b6a044c1d3ff70258ee008f3074c1cda7a0a7d3 +size 2494584960 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ2_XXS.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..706c00d --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18f7653a28fb668a6cf7238499b320e993a1aa8dc58b51cc859d118e95e3be7a +size 2288015488 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ3_M.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ3_M.gguf new file mode 100644 index 0000000..62dc722 --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c17cfec519a23cd3b99f7771f370bf8bce1bbaa09ad53582a12b11151f9fef57 +size 3648804992 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ3_S.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ3_S.gguf new file mode 100644 index 0000000..115f6b8 --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc345984627ee1f07e7305f6ef8c90a47fb0ba8d3844d29d9b9fdbb5828f80e5 +size 3546306688 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ3_XS.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ3_XS.gguf new file mode 100644 index 0000000..0d0fec7 --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7aca42bd79a3a544778b3e191a7aa238c3318cff7d6d67a0ecda4fe8328fe42 +size 3382728832 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ3_XXS.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..b59d4ba --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4ee7a140d291f96d31aa42f7e225238f729fb3b9761667ee937d41b7bfa84d8 +size 3152959616 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ4_NL.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ4_NL.gguf new file mode 100644 index 0000000..596ebbe --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b408be24f5f3703d08c41d80351265b3da6de2b3894c2008cce419b59613e99a +size 4527904896 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ4_XS.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ4_XS.gguf new file mode 100644 index 0000000..476a30a --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19d77157c0c4253037bf9283e3646c8bc9511949fe1a91c275fd9d6b052dbd69 +size 4300888192 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-Q2_K.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q2_K.gguf new file mode 100644 index 0000000..d1901fe --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b4ab1b15f83dce7de3e8b7c465f86caf7e905e897d28595771d61eb1adc7667 +size 3053869184 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-Q2_K_S.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q2_K_S.gguf new file mode 100644 index 0000000..0520c06 --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10abea64eac68e1e4e460460c27e849067484d7b648a2182a55827a6805b5709 +size 2863552640 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-Q3_K_L.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q3_K_L.gguf new file mode 100644 index 0000000..324efa4 --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbda04230bc44c5b510ceca140e67af402e8ce74937d8713745ff1b7075f419c +size 4185938048 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-Q3_K_M.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q3_K_M.gguf new file mode 100644 index 0000000..e7dab68 --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2206310324d3c2a5bee1f194f543838a634bcd00a8f66becdc805e15e2e3a32d +size 3882899584 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-Q3_K_S.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q3_K_S.gguf new file mode 100644 index 0000000..840f1b5 --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5334e18e555bc0ff402e4ffcc96012e6f9305e80413f5b5781e7dc13d1bb677f +size 3528480896 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-Q4_0.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q4_0.gguf new file mode 100644 index 0000000..082eed2 --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b03e5a2ba85847a85944b645ef3d31c49ad2c49671283c94e14158aea843fce9 +size 4525807744 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-Q4_1.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q4_1.gguf new file mode 100644 index 0000000..780c52d --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d67099108b60c9ab646f2a0127e7276b22807d78e5a9ce25888de78c9bb896a3 +size 4973549696 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-Q4_K_M.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q4_K_M.gguf new file mode 100644 index 0000000..b10c3b7 --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2d51fcdf95900462bfb3699961c71de486f76d4ef8d49f9b8d947bce3bb299b +size 4770650240 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-Q4_K_S.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q4_K_S.gguf new file mode 100644 index 0000000..e95d8b7 --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f351df956c9aecdf645ebc5b5fcc827fa5b1fc8a144575db283b1cc86057d3cb +size 4542584960 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-Q5_K_M.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q5_K_M.gguf new file mode 100644 index 0000000..83363a4 --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6736f931d74ffc11a56a3b9e7313416ae793b262098bb7e53a59cc4b2c7a35bf +size 5569665152 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-Q5_K_S.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q5_K_S.gguf new file mode 100644 index 0000000..3813c28 --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1d9ac51559139f32eaca06c05532447d8da0ad49278187cd5bc3a329384a9aa +size 5435971712 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.i1-Q6_K.gguf b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q6_K.gguf new file mode 100644 index 0000000..51da51e --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a14e92b93a7b9506bc14b49aee949fc9284534b0793ddde8bf04e495a1cecdee +size 6418618496 diff --git a/README.md b/README.md new file mode 100644 index 0000000..19f78ba --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: furiosa-ai-dev/EXAONE-3.0-7.8B-Instruct-converted +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/furiosa-ai-dev/EXAONE-3.0-7.8B-Instruct-converted + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-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/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ1_M.gguf) | i1-IQ1_M | 2.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.0 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-Q2_K.gguf) | i1-Q2_K | 3.2 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-Q4_0.gguf) | i1-Q4_0 | 4.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.6 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-Q4_1.gguf) | i1-Q4_1 | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-i1-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.i1-Q6_K.gguf) | i1-Q6_K | 6.5 | 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..36dd041 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebada919a0661fc72e2b28f8b8db1e11afe3f8764d0ede381ae28e52f5d41d82 +size 4988157