From c0eb7af350b8290547eb53b723f0bac306e4226e Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Wed, 22 Apr 2026 02:57:32 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/Llama-3-Aplite-Instruct-4x8B-i1-GGUF Source: Original Platform --- .gitattributes | 57 ++++++++++++++ Llama-3-Aplite-Instruct-4x8B.i1-IQ1_M.gguf | 3 + Llama-3-Aplite-Instruct-4x8B.i1-IQ1_S.gguf | 3 + Llama-3-Aplite-Instruct-4x8B.i1-IQ2_M.gguf | 3 + Llama-3-Aplite-Instruct-4x8B.i1-IQ2_S.gguf | 3 + Llama-3-Aplite-Instruct-4x8B.i1-IQ2_XS.gguf | 3 + Llama-3-Aplite-Instruct-4x8B.i1-IQ2_XXS.gguf | 3 + Llama-3-Aplite-Instruct-4x8B.i1-IQ3_M.gguf | 3 + Llama-3-Aplite-Instruct-4x8B.i1-IQ3_S.gguf | 3 + Llama-3-Aplite-Instruct-4x8B.i1-IQ3_XS.gguf | 3 + Llama-3-Aplite-Instruct-4x8B.i1-IQ3_XXS.gguf | 3 + Llama-3-Aplite-Instruct-4x8B.i1-IQ4_XS.gguf | 3 + Llama-3-Aplite-Instruct-4x8B.i1-Q2_K.gguf | 3 + Llama-3-Aplite-Instruct-4x8B.i1-Q3_K_L.gguf | 3 + Llama-3-Aplite-Instruct-4x8B.i1-Q3_K_M.gguf | 3 + Llama-3-Aplite-Instruct-4x8B.i1-Q3_K_S.gguf | 3 + Llama-3-Aplite-Instruct-4x8B.i1-Q4_0.gguf | 3 + Llama-3-Aplite-Instruct-4x8B.i1-Q4_K_M.gguf | 3 + Llama-3-Aplite-Instruct-4x8B.i1-Q4_K_S.gguf | 3 + Llama-3-Aplite-Instruct-4x8B.i1-Q5_K_M.gguf | 3 + Llama-3-Aplite-Instruct-4x8B.i1-Q5_K_S.gguf | 3 + Llama-3-Aplite-Instruct-4x8B.i1-Q6_K.gguf | 3 + README.md | 82 ++++++++++++++++++++ imatrix.dat | 3 + 24 files changed, 205 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama-3-Aplite-Instruct-4x8B.i1-IQ1_M.gguf create mode 100644 Llama-3-Aplite-Instruct-4x8B.i1-IQ1_S.gguf create mode 100644 Llama-3-Aplite-Instruct-4x8B.i1-IQ2_M.gguf create mode 100644 Llama-3-Aplite-Instruct-4x8B.i1-IQ2_S.gguf create mode 100644 Llama-3-Aplite-Instruct-4x8B.i1-IQ2_XS.gguf create mode 100644 Llama-3-Aplite-Instruct-4x8B.i1-IQ2_XXS.gguf create mode 100644 Llama-3-Aplite-Instruct-4x8B.i1-IQ3_M.gguf create mode 100644 Llama-3-Aplite-Instruct-4x8B.i1-IQ3_S.gguf create mode 100644 Llama-3-Aplite-Instruct-4x8B.i1-IQ3_XS.gguf create mode 100644 Llama-3-Aplite-Instruct-4x8B.i1-IQ3_XXS.gguf create mode 100644 Llama-3-Aplite-Instruct-4x8B.i1-IQ4_XS.gguf create mode 100644 Llama-3-Aplite-Instruct-4x8B.i1-Q2_K.gguf create mode 100644 Llama-3-Aplite-Instruct-4x8B.i1-Q3_K_L.gguf create mode 100644 Llama-3-Aplite-Instruct-4x8B.i1-Q3_K_M.gguf create mode 100644 Llama-3-Aplite-Instruct-4x8B.i1-Q3_K_S.gguf create mode 100644 Llama-3-Aplite-Instruct-4x8B.i1-Q4_0.gguf create mode 100644 Llama-3-Aplite-Instruct-4x8B.i1-Q4_K_M.gguf create mode 100644 Llama-3-Aplite-Instruct-4x8B.i1-Q4_K_S.gguf create mode 100644 Llama-3-Aplite-Instruct-4x8B.i1-Q5_K_M.gguf create mode 100644 Llama-3-Aplite-Instruct-4x8B.i1-Q5_K_S.gguf create mode 100644 Llama-3-Aplite-Instruct-4x8B.i1-Q6_K.gguf create mode 100644 README.md create mode 100644 imatrix.dat diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b2348a5 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +Llama-3-Aplite-Instruct-4x8B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Aplite-Instruct-4x8B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Aplite-Instruct-4x8B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Aplite-Instruct-4x8B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Aplite-Instruct-4x8B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Aplite-Instruct-4x8B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Aplite-Instruct-4x8B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Aplite-Instruct-4x8B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Aplite-Instruct-4x8B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Aplite-Instruct-4x8B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Aplite-Instruct-4x8B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Aplite-Instruct-4x8B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Aplite-Instruct-4x8B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Aplite-Instruct-4x8B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Aplite-Instruct-4x8B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Aplite-Instruct-4x8B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Aplite-Instruct-4x8B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Aplite-Instruct-4x8B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Aplite-Instruct-4x8B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Aplite-Instruct-4x8B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Aplite-Instruct-4x8B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-Aplite-Instruct-4x8B.i1-IQ1_M.gguf b/Llama-3-Aplite-Instruct-4x8B.i1-IQ1_M.gguf new file mode 100644 index 0000000..64b0d51 --- /dev/null +++ b/Llama-3-Aplite-Instruct-4x8B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45458052ab0d302cb95f108a577a16c4235af0ef7256d784e09bb633c09a9f7a +size 5939470848 diff --git a/Llama-3-Aplite-Instruct-4x8B.i1-IQ1_S.gguf b/Llama-3-Aplite-Instruct-4x8B.i1-IQ1_S.gguf new file mode 100644 index 0000000..19441b7 --- /dev/null +++ b/Llama-3-Aplite-Instruct-4x8B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7251f077b9d9e914abfa0d884afb732a09bff12c15a55610251ce148b84ff5e3 +size 5417280000 diff --git a/Llama-3-Aplite-Instruct-4x8B.i1-IQ2_M.gguf b/Llama-3-Aplite-Instruct-4x8B.i1-IQ2_M.gguf new file mode 100644 index 0000000..8628b8b --- /dev/null +++ b/Llama-3-Aplite-Instruct-4x8B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e092e944f97171644cfe3c732111d9ddbd5fa4da5a56a584b28e893467de2a5 +size 8443347456 diff --git a/Llama-3-Aplite-Instruct-4x8B.i1-IQ2_S.gguf b/Llama-3-Aplite-Instruct-4x8B.i1-IQ2_S.gguf new file mode 100644 index 0000000..3675eb6 --- /dev/null +++ b/Llama-3-Aplite-Instruct-4x8B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63ca987a11a374562ce4822cd1ed8881d3ea93877b2687d0cfb78d5213c2ee42 +size 7747092992 diff --git a/Llama-3-Aplite-Instruct-4x8B.i1-IQ2_XS.gguf b/Llama-3-Aplite-Instruct-4x8B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..172b438 --- /dev/null +++ b/Llama-3-Aplite-Instruct-4x8B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0f1ba447933eabb94addf30d7edf0ee96bbcf9be21c7b011ec9f347b2f85244 +size 7522820608 diff --git a/Llama-3-Aplite-Instruct-4x8B.i1-IQ2_XXS.gguf b/Llama-3-Aplite-Instruct-4x8B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..a6d1695 --- /dev/null +++ b/Llama-3-Aplite-Instruct-4x8B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86562bd70a210b2e65c644454834af920569ae3459b4a9c745bad16d3665c7f6 +size 6809788928 diff --git a/Llama-3-Aplite-Instruct-4x8B.i1-IQ3_M.gguf b/Llama-3-Aplite-Instruct-4x8B.i1-IQ3_M.gguf new file mode 100644 index 0000000..873e282 --- /dev/null +++ b/Llama-3-Aplite-Instruct-4x8B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43f54ba9159950053da5f068575a162949643943cafaa15134b57329aebac9f9 +size 11146093056 diff --git a/Llama-3-Aplite-Instruct-4x8B.i1-IQ3_S.gguf b/Llama-3-Aplite-Instruct-4x8B.i1-IQ3_S.gguf new file mode 100644 index 0000000..81f9545 --- /dev/null +++ b/Llama-3-Aplite-Instruct-4x8B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdc88b0d5facc6e5182d93fd8fe9f65d82fb21e72482d902caae0b88ec84d780 +size 10950009344 diff --git a/Llama-3-Aplite-Instruct-4x8B.i1-IQ3_XS.gguf b/Llama-3-Aplite-Instruct-4x8B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..c89b78c --- /dev/null +++ b/Llama-3-Aplite-Instruct-4x8B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2cfd267c1d608b0db7738ed13dc9b46aa8169a60faa262ff2525c2bcd3dbd62 +size 10390069760 diff --git a/Llama-3-Aplite-Instruct-4x8B.i1-IQ3_XXS.gguf b/Llama-3-Aplite-Instruct-4x8B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..c1bbb59 --- /dev/null +++ b/Llama-3-Aplite-Instruct-4x8B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:226b83004b9b691394617e366bfce1400a9bd035c06a950ee69ebb434ea98022 +size 9749873152 diff --git a/Llama-3-Aplite-Instruct-4x8B.i1-IQ4_XS.gguf b/Llama-3-Aplite-Instruct-4x8B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..8520d03 --- /dev/null +++ b/Llama-3-Aplite-Instruct-4x8B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:851ff4eade838731340259519d5d5bef2b319410770b6fdaa74cc9c7205b9497 +size 13432914432 diff --git a/Llama-3-Aplite-Instruct-4x8B.i1-Q2_K.gguf b/Llama-3-Aplite-Instruct-4x8B.i1-Q2_K.gguf new file mode 100644 index 0000000..40ddccb --- /dev/null +++ b/Llama-3-Aplite-Instruct-4x8B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7617cc2c393ad76afd2eaca75fbd8e73c644d9e178e08af12f222f3bcb3faa60 +size 9301770752 diff --git a/Llama-3-Aplite-Instruct-4x8B.i1-Q3_K_L.gguf b/Llama-3-Aplite-Instruct-4x8B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..5be14ba --- /dev/null +++ b/Llama-3-Aplite-Instruct-4x8B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:554885fe513664ae500619cb208daaf009f052b9f131bdf6323af296f44d2b9e +size 13042967040 diff --git a/Llama-3-Aplite-Instruct-4x8B.i1-Q3_K_M.gguf b/Llama-3-Aplite-Instruct-4x8B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..85adc67 --- /dev/null +++ b/Llama-3-Aplite-Instruct-4x8B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02ea8109e818eef9adc4e28476bead09674ccf216ca317ef355e23fa4956e0f8 +size 12079325696 diff --git a/Llama-3-Aplite-Instruct-4x8B.i1-Q3_K_S.gguf b/Llama-3-Aplite-Instruct-4x8B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..8a1755a --- /dev/null +++ b/Llama-3-Aplite-Instruct-4x8B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe1c2bd2daf67d498f3f68447d109dddefd77003125a569cfca00476b7ace4ae +size 10932183552 diff --git a/Llama-3-Aplite-Instruct-4x8B.i1-Q4_0.gguf b/Llama-3-Aplite-Instruct-4x8B.i1-Q4_0.gguf new file mode 100644 index 0000000..905697c --- /dev/null +++ b/Llama-3-Aplite-Instruct-4x8B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b54686f66da38c267c57c32323a7503bc34b0095e3e6f08ae7324d750b1a4a7 +size 14233666048 diff --git a/Llama-3-Aplite-Instruct-4x8B.i1-Q4_K_M.gguf b/Llama-3-Aplite-Instruct-4x8B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..63deeb5 --- /dev/null +++ b/Llama-3-Aplite-Instruct-4x8B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b464061e1ea02dd5c0b5142037f3930e8ed9bf850cc49a173af3d1267cb6e4af +size 15161131520 diff --git a/Llama-3-Aplite-Instruct-4x8B.i1-Q4_K_S.gguf b/Llama-3-Aplite-Instruct-4x8B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..afd7b64 --- /dev/null +++ b/Llama-3-Aplite-Instruct-4x8B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45ea0d031961b9f866b82340b5007fff696ec7e48ee08ed7e8260eac81d8d5bd +size 14294483456 diff --git a/Llama-3-Aplite-Instruct-4x8B.i1-Q5_K_M.gguf b/Llama-3-Aplite-Instruct-4x8B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..9317ed1 --- /dev/null +++ b/Llama-3-Aplite-Instruct-4x8B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0247aa3d5ff46c0084f7ca21cf1bac68c77734579ca1a41317c57cd5933d1419 +size 17734992384 diff --git a/Llama-3-Aplite-Instruct-4x8B.i1-Q5_K_S.gguf b/Llama-3-Aplite-Instruct-4x8B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..d73ca7a --- /dev/null +++ b/Llama-3-Aplite-Instruct-4x8B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71a5bee4ef557af679ec520831c7b078fe16aa590a00ae06bc5523bda6463dd3 +size 17226957312 diff --git a/Llama-3-Aplite-Instruct-4x8B.i1-Q6_K.gguf b/Llama-3-Aplite-Instruct-4x8B.i1-Q6_K.gguf new file mode 100644 index 0000000..c8a6f8e --- /dev/null +++ b/Llama-3-Aplite-Instruct-4x8B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c04cbd8f1e1a08a232d9054130224d2c695706a33c5b29b96019bbcda41ed76 +size 20469719552 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9a94d8a --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: raincandy-u/Llama-3-Aplite-Instruct-4x8B-MoE +language: +- en +library_name: transformers +license: other +license_link: LICENSE +license_name: llama3 +quantized_by: mradermacher +tags: +- facebook +- meta +- pytorch +- llama +- llama-3 +- moe +- code +--- +## About + + + + + +weighted/imatrix quants of https://huggingface.co/raincandy-u/Llama-3-Aplite-Instruct-4x8B-MoE + + +static quants are available at https://huggingface.co/mradermacher/Llama-3-Aplite-Instruct-4x8B-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/Llama-3-Aplite-Instruct-4x8B-i1-GGUF/resolve/main/Llama-3-Aplite-Instruct-4x8B.i1-IQ1_S.gguf) | i1-IQ1_S | 5.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Aplite-Instruct-4x8B-i1-GGUF/resolve/main/Llama-3-Aplite-Instruct-4x8B.i1-IQ1_M.gguf) | i1-IQ1_M | 6.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Aplite-Instruct-4x8B-i1-GGUF/resolve/main/Llama-3-Aplite-Instruct-4x8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Aplite-Instruct-4x8B-i1-GGUF/resolve/main/Llama-3-Aplite-Instruct-4x8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 7.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Aplite-Instruct-4x8B-i1-GGUF/resolve/main/Llama-3-Aplite-Instruct-4x8B.i1-IQ2_S.gguf) | i1-IQ2_S | 7.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Aplite-Instruct-4x8B-i1-GGUF/resolve/main/Llama-3-Aplite-Instruct-4x8B.i1-IQ2_M.gguf) | i1-IQ2_M | 8.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Aplite-Instruct-4x8B-i1-GGUF/resolve/main/Llama-3-Aplite-Instruct-4x8B.i1-Q2_K.gguf) | i1-Q2_K | 9.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Aplite-Instruct-4x8B-i1-GGUF/resolve/main/Llama-3-Aplite-Instruct-4x8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 9.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Aplite-Instruct-4x8B-i1-GGUF/resolve/main/Llama-3-Aplite-Instruct-4x8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 10.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Aplite-Instruct-4x8B-i1-GGUF/resolve/main/Llama-3-Aplite-Instruct-4x8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 11.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Aplite-Instruct-4x8B-i1-GGUF/resolve/main/Llama-3-Aplite-Instruct-4x8B.i1-IQ3_S.gguf) | i1-IQ3_S | 11.1 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Aplite-Instruct-4x8B-i1-GGUF/resolve/main/Llama-3-Aplite-Instruct-4x8B.i1-IQ3_M.gguf) | i1-IQ3_M | 11.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Aplite-Instruct-4x8B-i1-GGUF/resolve/main/Llama-3-Aplite-Instruct-4x8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 12.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Aplite-Instruct-4x8B-i1-GGUF/resolve/main/Llama-3-Aplite-Instruct-4x8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 13.1 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Aplite-Instruct-4x8B-i1-GGUF/resolve/main/Llama-3-Aplite-Instruct-4x8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 13.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Aplite-Instruct-4x8B-i1-GGUF/resolve/main/Llama-3-Aplite-Instruct-4x8B.i1-Q4_0.gguf) | i1-Q4_0 | 14.3 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Aplite-Instruct-4x8B-i1-GGUF/resolve/main/Llama-3-Aplite-Instruct-4x8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.4 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Aplite-Instruct-4x8B-i1-GGUF/resolve/main/Llama-3-Aplite-Instruct-4x8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 15.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Aplite-Instruct-4x8B-i1-GGUF/resolve/main/Llama-3-Aplite-Instruct-4x8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 17.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Aplite-Instruct-4x8B-i1-GGUF/resolve/main/Llama-3-Aplite-Instruct-4x8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 17.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Aplite-Instruct-4x8B-i1-GGUF/resolve/main/Llama-3-Aplite-Instruct-4x8B.i1-Q6_K.gguf) | i1-Q6_K | 20.6 | 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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..fd7130e --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0faddd5e7023248f36047701c36475c05cb8338423e5bb13b848eb0fc15ee2c7 +size 14164885