From bc4d4d336b0f15388c31fa8abdaebca8a5fb2ee4 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 18 May 2026 06:30:14 +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-3.2-3B-Sci-Think-i1-GGUF Source: Original Platform --- .gitattributes | 60 +++++++++++++++++++ Llama-3.2-3B-Sci-Think.i1-IQ1_M.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-IQ1_S.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-IQ2_M.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-IQ2_S.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-IQ2_XS.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-IQ2_XXS.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-IQ3_M.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-IQ3_S.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-IQ3_XS.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-IQ3_XXS.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-IQ4_XS.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-Q2_K.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-Q3_K_L.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-Q3_K_M.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-Q3_K_S.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-Q4_0.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-Q4_0_4_4.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-Q4_0_4_8.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-Q4_0_8_8.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-Q4_K_M.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-Q4_K_S.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-Q5_K_M.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-Q5_K_S.gguf | 3 + Llama-3.2-3B-Sci-Think.i1-Q6_K.gguf | 3 + README.md | 78 +++++++++++++++++++++++++ imatrix.dat | 3 + 27 files changed, 213 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama-3.2-3B-Sci-Think.i1-IQ1_M.gguf create mode 100644 Llama-3.2-3B-Sci-Think.i1-IQ1_S.gguf create mode 100644 Llama-3.2-3B-Sci-Think.i1-IQ2_M.gguf create mode 100644 Llama-3.2-3B-Sci-Think.i1-IQ2_S.gguf create mode 100644 Llama-3.2-3B-Sci-Think.i1-IQ2_XS.gguf create mode 100644 Llama-3.2-3B-Sci-Think.i1-IQ2_XXS.gguf create mode 100644 Llama-3.2-3B-Sci-Think.i1-IQ3_M.gguf create mode 100644 Llama-3.2-3B-Sci-Think.i1-IQ3_S.gguf create mode 100644 Llama-3.2-3B-Sci-Think.i1-IQ3_XS.gguf create mode 100644 Llama-3.2-3B-Sci-Think.i1-IQ3_XXS.gguf create mode 100644 Llama-3.2-3B-Sci-Think.i1-IQ4_XS.gguf create mode 100644 Llama-3.2-3B-Sci-Think.i1-Q2_K.gguf create mode 100644 Llama-3.2-3B-Sci-Think.i1-Q3_K_L.gguf create mode 100644 Llama-3.2-3B-Sci-Think.i1-Q3_K_M.gguf create mode 100644 Llama-3.2-3B-Sci-Think.i1-Q3_K_S.gguf create mode 100644 Llama-3.2-3B-Sci-Think.i1-Q4_0.gguf create mode 100644 Llama-3.2-3B-Sci-Think.i1-Q4_0_4_4.gguf create mode 100644 Llama-3.2-3B-Sci-Think.i1-Q4_0_4_8.gguf create mode 100644 Llama-3.2-3B-Sci-Think.i1-Q4_0_8_8.gguf create mode 100644 Llama-3.2-3B-Sci-Think.i1-Q4_K_M.gguf create mode 100644 Llama-3.2-3B-Sci-Think.i1-Q4_K_S.gguf create mode 100644 Llama-3.2-3B-Sci-Think.i1-Q5_K_M.gguf create mode 100644 Llama-3.2-3B-Sci-Think.i1-Q5_K_S.gguf create mode 100644 Llama-3.2-3B-Sci-Think.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..6b19b61 --- /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 +Llama-3.2-3B-Sci-Think.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Sci-Think.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Sci-Think.i1-IQ1_M.gguf b/Llama-3.2-3B-Sci-Think.i1-IQ1_M.gguf new file mode 100644 index 0000000..1977c80 --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0621257d8e85b2f1d8adbd97ded0dc3fe207be99297f100d81e07cd7c49fb997 +size 924192128 diff --git a/Llama-3.2-3B-Sci-Think.i1-IQ1_S.gguf b/Llama-3.2-3B-Sci-Think.i1-IQ1_S.gguf new file mode 100644 index 0000000..6d88e6e --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b5dc0579ccee8176bc78e28144bd62156a53524f02afff132269ab92ec404da +size 868158848 diff --git a/Llama-3.2-3B-Sci-Think.i1-IQ2_M.gguf b/Llama-3.2-3B-Sci-Think.i1-IQ2_M.gguf new file mode 100644 index 0000000..c89c20e --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0e9fe2e333e16b0ecb7211f56bb4a865f77ddd9ddd3e50ffb904bfa21b28773 +size 1229032832 diff --git a/Llama-3.2-3B-Sci-Think.i1-IQ2_S.gguf b/Llama-3.2-3B-Sci-Think.i1-IQ2_S.gguf new file mode 100644 index 0000000..afca9f1 --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11f89559a8c76f0b0dd89d8a7694443e409e9c8bef6cd885edad4e66ebe7ceb5 +size 1154321792 diff --git a/Llama-3.2-3B-Sci-Think.i1-IQ2_XS.gguf b/Llama-3.2-3B-Sci-Think.i1-IQ2_XS.gguf new file mode 100644 index 0000000..edbc812 --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46a430eab692ba6459ee89916dbed24b8230ca0259c5cd7776a3eedf03350942 +size 1100549504 diff --git a/Llama-3.2-3B-Sci-Think.i1-IQ2_XXS.gguf b/Llama-3.2-3B-Sci-Think.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..3801607 --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c74efddc5ba90d649752832f8c68717e749168f7f75d35699b60a5e62c38a1b2 +size 1017580928 diff --git a/Llama-3.2-3B-Sci-Think.i1-IQ3_M.gguf b/Llama-3.2-3B-Sci-Think.i1-IQ3_M.gguf new file mode 100644 index 0000000..49d69ed --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eb3fd5ed4e8d40810526040f777141252b1d7baaf4f8cd4f90e0df845ab93d4 +size 1599669632 diff --git a/Llama-3.2-3B-Sci-Think.i1-IQ3_S.gguf b/Llama-3.2-3B-Sci-Think.i1-IQ3_S.gguf new file mode 100644 index 0000000..6902a43 --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a9563c442dbe7b6e50f99df87329e833abcf2c603ab37080a90cb4adfae17ea +size 1542849920 diff --git a/Llama-3.2-3B-Sci-Think.i1-IQ3_XS.gguf b/Llama-3.2-3B-Sci-Think.i1-IQ3_XS.gguf new file mode 100644 index 0000000..24b76bb --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0645409588bfd918e98223b071c3ef5762881cb7ddf8b662840f6e6984a350aa +size 1476789632 diff --git a/Llama-3.2-3B-Sci-Think.i1-IQ3_XXS.gguf b/Llama-3.2-3B-Sci-Think.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..ee15609 --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2393de5981b9ad1b1c8e0943cc87c6572c88e09d4bce0d0e955f70f9ae0f2a6 +size 1348767104 diff --git a/Llama-3.2-3B-Sci-Think.i1-IQ4_XS.gguf b/Llama-3.2-3B-Sci-Think.i1-IQ4_XS.gguf new file mode 100644 index 0000000..3e150bd --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6488d4c6323bf446c2ccdfa736ec88583df50d4816b0ab7da25d5cfdb701097f +size 1829111168 diff --git a/Llama-3.2-3B-Sci-Think.i1-Q2_K.gguf b/Llama-3.2-3B-Sci-Think.i1-Q2_K.gguf new file mode 100644 index 0000000..39495ad --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d77afe3576ce08f5556903750fa63c4fa09c793e42adc42dd7480adc2dc907a2 +size 1363936640 diff --git a/Llama-3.2-3B-Sci-Think.i1-Q3_K_L.gguf b/Llama-3.2-3B-Sci-Think.i1-Q3_K_L.gguf new file mode 100644 index 0000000..41f617e --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28da499b6e7ecc3a0ce57dbd910b6ef74648c7717f350796c4e69f0bb4e4ac1f +size 1815348608 diff --git a/Llama-3.2-3B-Sci-Think.i1-Q3_K_M.gguf b/Llama-3.2-3B-Sci-Think.i1-Q3_K_M.gguf new file mode 100644 index 0000000..6698918 --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d6977b29007451d612ee4e429bb60cb072c9bb4ee89c513e5bd872f4972eb94 +size 1687160192 diff --git a/Llama-3.2-3B-Sci-Think.i1-Q3_K_S.gguf b/Llama-3.2-3B-Sci-Think.i1-Q3_K_S.gguf new file mode 100644 index 0000000..5ce294a --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c40e0e8c903b4b706d05ed96928b36cb43424ae84e70b30b860a84c2e00a5acb +size 1542849920 diff --git a/Llama-3.2-3B-Sci-Think.i1-Q4_0.gguf b/Llama-3.2-3B-Sci-Think.i1-Q4_0.gguf new file mode 100644 index 0000000..50d2697 --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7cf3c9bd0b12d340f2e18a0b302be841254b368b0e5f723a855846b10c726a8 +size 1921910144 diff --git a/Llama-3.2-3B-Sci-Think.i1-Q4_0_4_4.gguf b/Llama-3.2-3B-Sci-Think.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..ebbd17c --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71619860b9009fafc286df16f2f8b01a65f1e58409c762fc98d60c79629c8dba +size 1917191552 diff --git a/Llama-3.2-3B-Sci-Think.i1-Q4_0_4_8.gguf b/Llama-3.2-3B-Sci-Think.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..2c64933 --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10b666b4ba153164a27a22bef01b317b5af94105dd2641b1c5e114dbeecc26e5 +size 1917191552 diff --git a/Llama-3.2-3B-Sci-Think.i1-Q4_0_8_8.gguf b/Llama-3.2-3B-Sci-Think.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..a31a3c1 --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb8f2bc30c16f38524a6965e4e0bec5f15306786ac47163abb8132473f0784c8 +size 1917191552 diff --git a/Llama-3.2-3B-Sci-Think.i1-Q4_K_M.gguf b/Llama-3.2-3B-Sci-Think.i1-Q4_K_M.gguf new file mode 100644 index 0000000..83f0819 --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33cc2b5e541e5da73cd9907c3ac8cb39a4eb9ce3b656f796cd8a4f7fe2937e49 +size 2019378560 diff --git a/Llama-3.2-3B-Sci-Think.i1-Q4_K_S.gguf b/Llama-3.2-3B-Sci-Think.i1-Q4_K_S.gguf new file mode 100644 index 0000000..e06ac0d --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7315349e6ba805b9928d4eeb6a44f6f8f98eeb919ccaa610ed184ee1ac577570 +size 1928201600 diff --git a/Llama-3.2-3B-Sci-Think.i1-Q5_K_M.gguf b/Llama-3.2-3B-Sci-Think.i1-Q5_K_M.gguf new file mode 100644 index 0000000..ecdef26 --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93ffefbb2dff6b047692e4e2eeb2b3e995faad5c112b252c15afcd87cf218b1d +size 2322154880 diff --git a/Llama-3.2-3B-Sci-Think.i1-Q5_K_S.gguf b/Llama-3.2-3B-Sci-Think.i1-Q5_K_S.gguf new file mode 100644 index 0000000..cae56b3 --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a47f66bab0802a9b3d61ce36348077b571dc15eb4c904bff842e58b020e9fce +size 2269513088 diff --git a/Llama-3.2-3B-Sci-Think.i1-Q6_K.gguf b/Llama-3.2-3B-Sci-Think.i1-Q6_K.gguf new file mode 100644 index 0000000..7e41a1a --- /dev/null +++ b/Llama-3.2-3B-Sci-Think.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaa2b35339fc703309da934bda4bd6eb4ef5ea126b25e309dff61845058072b3 +size 2643854720 diff --git a/README.md b/README.md new file mode 100644 index 0000000..da8bc74 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: bunnycore/Llama-3.2-3B-Sci-Think +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/bunnycore/Llama-3.2-3B-Sci-Think + + +static quants are available at https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-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-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 2.0 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 2.0 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 2.0 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Sci-Think-i1-GGUF/resolve/main/Llama-3.2-3B-Sci-Think.i1-Q6_K.gguf) | i1-Q6_K | 2.7 | 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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..1511ffc --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f8640614ff07962024e9a600359e8a23f589e03e7a6f74f425979e698711486 +size 2988377