commit e0f8897d3f3914affe9a295e1d6c0ce2b56e0b79 Author: ModelHub XC Date: Sat Jun 27 02:30:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ef7af99 --- /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 +LUFFY-Qwen-Instruct-7B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY-Qwen-Instruct-7B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LUFFY-Qwen-Instruct-7B.i1-IQ1_M.gguf b/LUFFY-Qwen-Instruct-7B.i1-IQ1_M.gguf new file mode 100644 index 0000000..58733d7 --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51749a557d984a44fbf21c72563cde3259828932a573b3d7e64f2f826d817cf4 +size 2042196928 diff --git a/LUFFY-Qwen-Instruct-7B.i1-IQ1_S.gguf b/LUFFY-Qwen-Instruct-7B.i1-IQ1_S.gguf new file mode 100644 index 0000000..5d3c893 --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f55337225a0c4265f14671398e1130cd289338950c1e65479fd15848226384e6 +size 1903668160 diff --git a/LUFFY-Qwen-Instruct-7B.i1-IQ2_M.gguf b/LUFFY-Qwen-Instruct-7B.i1-IQ2_M.gguf new file mode 100644 index 0000000..45ada6d --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d53afc9cf26d03cc6c4473fddab4114cd61563c1d00b8735282b985d63ccb1f6 +size 2780343232 diff --git a/LUFFY-Qwen-Instruct-7B.i1-IQ2_S.gguf b/LUFFY-Qwen-Instruct-7B.i1-IQ2_S.gguf new file mode 100644 index 0000000..7f66a2f --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5bf971e79a8e7201723c4c50ee8f1bc83c1cf28d590c4d0afa7430f3420fac1 +size 2595638208 diff --git a/LUFFY-Qwen-Instruct-7B.i1-IQ2_XS.gguf b/LUFFY-Qwen-Instruct-7B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..7c4b31b --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7054980f5fa4089e4b55db7e1a0ef858ee3b9d7b5f09735a72e21161e6b3870b +size 2469022656 diff --git a/LUFFY-Qwen-Instruct-7B.i1-IQ2_XXS.gguf b/LUFFY-Qwen-Instruct-7B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..bac9a93 --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:685dd21085e4f42c27e6d995d4481a8b3f60bfb773d64c244dcb75f1149b7db9 +size 2273078208 diff --git a/LUFFY-Qwen-Instruct-7B.i1-IQ3_M.gguf b/LUFFY-Qwen-Instruct-7B.i1-IQ3_M.gguf new file mode 100644 index 0000000..694447a --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5710c907e2f75608c8cb3f9e7bbf51d3516bb67fae1cc2245189e940e04d0817 +size 3574012864 diff --git a/LUFFY-Qwen-Instruct-7B.i1-IQ3_S.gguf b/LUFFY-Qwen-Instruct-7B.i1-IQ3_S.gguf new file mode 100644 index 0000000..0c0a780 --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64f114961339906da157b6d19bcfbc55f6dd3669abd0208fe6e635d796828efa +size 3499193280 diff --git a/LUFFY-Qwen-Instruct-7B.i1-IQ3_XS.gguf b/LUFFY-Qwen-Instruct-7B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..00cd6f6 --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1a748941184a29786e9fd2d66894e20910a34af5a42367f1a26988ff04034fb +size 3346256832 diff --git a/LUFFY-Qwen-Instruct-7B.i1-IQ3_XXS.gguf b/LUFFY-Qwen-Instruct-7B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..9ad3bbe --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07ff8a988a9cb2bd02a7059704408d10e824749d942fcdc24c1554c3de4d9edb +size 3114515392 diff --git a/LUFFY-Qwen-Instruct-7B.i1-IQ4_NL.gguf b/LUFFY-Qwen-Instruct-7B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..cb8cf19 --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11944209752be6fbee721b402f112e677b579162d81a2bf8385d1f862d5f3fbd +size 4437814208 diff --git a/LUFFY-Qwen-Instruct-7B.i1-IQ4_XS.gguf b/LUFFY-Qwen-Instruct-7B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..c6674ca --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:297f1fc25e84d16fa94493df1ee2a71fe8726bb8c0b1f82d38eaca65343d9b05 +size 4218473408 diff --git a/LUFFY-Qwen-Instruct-7B.i1-Q2_K.gguf b/LUFFY-Qwen-Instruct-7B.i1-Q2_K.gguf new file mode 100644 index 0000000..3c60bd6 --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd79b266ed0753cc4eb91efdbf0f858ff63177887040260660484ef89bc2824c +size 3015941056 diff --git a/LUFFY-Qwen-Instruct-7B.i1-Q2_K_S.gguf b/LUFFY-Qwen-Instruct-7B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..4483d71 --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21d945e4ad021cddec95873a6e99d88365007604f20134f3dc307b03e1230e18 +size 2834074560 diff --git a/LUFFY-Qwen-Instruct-7B.i1-Q3_K_L.gguf b/LUFFY-Qwen-Instruct-7B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..1089cba --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78ee962bc3ec065e9ec7815b2635d73e32a4a4793b4ebf48ced4638bc771b1b5 +size 4088460224 diff --git a/LUFFY-Qwen-Instruct-7B.i1-Q3_K_M.gguf b/LUFFY-Qwen-Instruct-7B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..2cdc44a --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd66f0b9dc1c455bb5c29cbe61368141daa76da4105e853a53a9023cba9da1b2 +size 3808392128 diff --git a/LUFFY-Qwen-Instruct-7B.i1-Q3_K_S.gguf b/LUFFY-Qwen-Instruct-7B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..4f88ffe --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0fb5227e0cab8c6d05a2d99e8abf4d92e4d7c7d9a9549ddecf97f016b93ea00 +size 3492369344 diff --git a/LUFFY-Qwen-Instruct-7B.i1-Q4_0.gguf b/LUFFY-Qwen-Instruct-7B.i1-Q4_0.gguf new file mode 100644 index 0000000..ef83e94 --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41a56dbedd5799cef90765228c0cb2b608352d60223885d914c5a75aec863441 +size 4444122048 diff --git a/LUFFY-Qwen-Instruct-7B.i1-Q4_1.gguf b/LUFFY-Qwen-Instruct-7B.i1-Q4_1.gguf new file mode 100644 index 0000000..050d68d --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:776c859c07d5c69116e6e24d555b58824b043e0a3f243186c0227d821c0391f2 +size 4873284544 diff --git a/LUFFY-Qwen-Instruct-7B.i1-Q4_K_M.gguf b/LUFFY-Qwen-Instruct-7B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..af81ef0 --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:876bb9cf8b3104e5bee61eb648c00f769faea775b6380e88158ed97448a1de02 +size 4683074496 diff --git a/LUFFY-Qwen-Instruct-7B.i1-Q4_K_S.gguf b/LUFFY-Qwen-Instruct-7B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..e6fbdb3 --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ceabba0cada7a859af242bbd1518e6d6a8becf722141679a7217746c83a1a918 +size 4457769920 diff --git a/LUFFY-Qwen-Instruct-7B.i1-Q5_K_M.gguf b/LUFFY-Qwen-Instruct-7B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..5b81685 --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd2e3d74e20bd014150c233bafc433315cb5d21dc437be65fd88d56a42f3e666 +size 5444832192 diff --git a/LUFFY-Qwen-Instruct-7B.i1-Q5_K_S.gguf b/LUFFY-Qwen-Instruct-7B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..a1be8c4 --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c639e75db0af61963467ee617c335d05594c8f0c1d183a96dc9382406abd5e1 +size 5315177408 diff --git a/LUFFY-Qwen-Instruct-7B.i1-Q6_K.gguf b/LUFFY-Qwen-Instruct-7B.i1-Q6_K.gguf new file mode 100644 index 0000000..a761621 --- /dev/null +++ b/LUFFY-Qwen-Instruct-7B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ef4d53dde6b6d10714ec0371d176cc05aec77a28c96bbf2d05a38bebe294e21 +size 6254199744 diff --git a/README.md b/README.md new file mode 100644 index 0000000..926338b --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: Elliott/LUFFY-Qwen-Instruct-7B +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- reasoning +- Zero-RL +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Elliott/LUFFY-Qwen-Instruct-7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LUFFY-Qwen-Instruct-7B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-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/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.9 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-Q4_1.gguf) | i1-Q4_1 | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/LUFFY-Qwen-Instruct-7B-i1-GGUF/resolve/main/LUFFY-Qwen-Instruct-7B.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | 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..6b41a27 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70335dcf0e33758706bfaf74a6d32d49236a8e1a4dcf34a9715b558dc31c944d +size 4536665