commit 2eadef3d2fc4009e8ba6f8b676851bed9746ab7b Author: ModelHub XC Date: Tue Jun 9 01:16:16 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6291e0 --- /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 +Nafha-Llama3.1-8B-Perfumery-Expert-v1.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ1_M.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ1_M.gguf new file mode 100644 index 0000000..8f8fc0c --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24758a73b325bb7f8ad922d293bf28e6d1f90f63cb8242994697cd5b626b3bc4 +size 2161977920 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ1_S.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ1_S.gguf new file mode 100644 index 0000000..2c16c5d --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb4683ea0e8385f28c09dbeadd7466d3e30bcbfbc350c14e610ee0b1a13c43f2 +size 2019633728 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ2_M.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ2_M.gguf new file mode 100644 index 0000000..5e412e1 --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55751f298a31d770a471d8747e6236e82fcdf632054cf690e3b4221c0b2a15c3 +size 2948287040 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ2_S.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ2_S.gguf new file mode 100644 index 0000000..9c67c30 --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:314220659f4568338df3841ff715ef72f10afe6920803a991960a807b41c9ef8 +size 2758494784 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ2_XS.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ2_XS.gguf new file mode 100644 index 0000000..6e733bd --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:623a10924810d0b35f3ed0aed067621421ae07690b2dfe66316aba0161d26deb +size 2605787712 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ2_XXS.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..e04bbe1 --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff45265d7c04e510d20b4e531cba74dcefbd8d7529f2bcdc61a542ca53ab6733 +size 2399218240 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ3_M.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ3_M.gguf new file mode 100644 index 0000000..3fdc8d0 --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe6a0fd6470ba655a70b17961781f60246b516e6a1bab8824c3861d508ea8916 +size 3784829504 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ3_S.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ3_S.gguf new file mode 100644 index 0000000..91149b4 --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e3a23fcb1f3c6e06fc944f561295e1bf2cd92e78248821fa47ef1218776ccfa +size 3682331200 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ3_XS.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ3_XS.gguf new file mode 100644 index 0000000..48eb6e7 --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b741f6799244b5a9117de4322f0863c3b5c2cc0d268b8fa208a27e115d027d9 +size 3518753344 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ3_XXS.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..195d19d --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ec629f269670514ae8f241e6be59e2d3c45455f9ae5539966bd66f219fd4a5b +size 3274918464 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ4_NL.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ4_NL.gguf new file mode 100644 index 0000000..48184a3 --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe8b3e23fafdb8ec35c17c0d218bdd27ef4903cc28102204144a704fd2887640 +size 4677995072 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ4_XS.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ4_XS.gguf new file mode 100644 index 0000000..ed47380 --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc9b497aeaecb76b3150fa9ca949ba1dbf1e00926bc5a2cfed888e664848bb7d +size 4447668800 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q2_K.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q2_K.gguf new file mode 100644 index 0000000..3332979 --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0ba231d5be765c687d340c6d4a2865875e49bfa09134f5792a7b0a6a552da50 +size 3179137600 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q2_K_S.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q2_K_S.gguf new file mode 100644 index 0000000..dfa5aff --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac5ac47bf391d6eb3c683ae9a8db3c42e14ff0a28f6986d588076b2938f6f7e1 +size 2988821056 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q3_K_L.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q3_K_L.gguf new file mode 100644 index 0000000..84655a6 --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6855c6e78f7db10e4ed6aeeab2c27b194154609a760653f2d9923682e6df850 +size 4321962560 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q3_K_M.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q3_K_M.gguf new file mode 100644 index 0000000..a2a4683 --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59520d59607275fad28e0b75d692a2bc25b723052ac78e605a978c68c23e2548 +size 4018924096 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q3_K_S.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q3_K_S.gguf new file mode 100644 index 0000000..bd634c3 --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fd117010d3653bfa98c42ee84184c93c25a6295eeafeab8e5f6044f908f88b4 +size 3664505408 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q4_0.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q4_0.gguf new file mode 100644 index 0000000..70014b6 --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aabe0c3ed756988045302142e0b883caedfee8af8eabf074c3025ce0623ecf27 +size 4675897920 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q4_1.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q4_1.gguf new file mode 100644 index 0000000..cf08046 --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd79620816b2ca8c99f7d8f8ab5844c839e28e51ea668fc416cfa5d7b6c1b72c +size 5130259008 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q4_K_M.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q4_K_M.gguf new file mode 100644 index 0000000..932e0b6 --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc8a7b9c3878bc8b7aafd9c97fbda62fda99d7df82bc2748e9cae211ffdf1d0b +size 4920740416 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q4_K_S.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q4_K_S.gguf new file mode 100644 index 0000000..a4e4483 --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4620838b72ac37174bd5fe8db01c09cbe91c6b99347b15f817e84af959db587 +size 4692675136 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q5_K_M.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q5_K_M.gguf new file mode 100644 index 0000000..cf9004b --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60eecf7572504c19bf34ac4b13af5a37edc6f9c2402fef7acb3b7e8ff4718dd6 +size 5732993600 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q5_K_S.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q5_K_S.gguf new file mode 100644 index 0000000..4449318 --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f96612b931c23d833b6b26156b4542048623706a3ec26e236b2a92255d37c017 +size 5599300160 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q6_K.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q6_K.gguf new file mode 100644 index 0000000..d517765 --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ca16baac61a07bba2a96d97580176b31e8d710333efd2034c77597ba0278fa7 +size 6596012608 diff --git a/Nafha-Llama3.1-8B-Perfumery-Expert-v1.imatrix.gguf b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.imatrix.gguf new file mode 100644 index 0000000..27e6859 --- /dev/null +++ b/Nafha-Llama3.1-8B-Perfumery-Expert-v1.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9039026959f5a438d6517c505e45fdcf58bdc14cf1ae4f69fd9c40b05fdfbf2c +size 5015200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3fab6ca --- /dev/null +++ b/README.md @@ -0,0 +1,97 @@ +--- +base_model: mohdAlal1/Nafha-Llama3.1-8B-Perfumery-Expert-v1 +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- unsloth +- llama +- llama-3 +- text-generation +- conversational +- perfumery +- fragrance +- domain-specific +- qlora +- fine-tuned +- neuroscent +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/mohdAlal1/Nafha-Llama3.1-8B-Perfumery-Expert-v1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-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/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Nafha-Llama3.1-8B-Perfumery-Expert-v1-i1-GGUF/resolve/main/Nafha-Llama3.1-8B-Perfumery-Expert-v1.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. + +