commit 91e72b60858e15d1953bfd861215cc835cd70e7e Author: ModelHub XC Date: Tue May 19 02:52:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e69bb27 --- /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-3.1-8B-ArliAI-RPMax-v1.2.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ1_M.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ1_M.gguf new file mode 100644 index 0000000..8c56f5a --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d764104b160f48720410788388a96f202fca4de19384ed604230633f63a6c473 +size 2161972736 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ1_S.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ1_S.gguf new file mode 100644 index 0000000..0b1a00c --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29b2545dad9540f99fb98aa393f5252d2135e0b8003124ffb8e064d0c021c4e9 +size 2019628544 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ2_M.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ2_M.gguf new file mode 100644 index 0000000..b27bd49 --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:225ff882b5e2b1b18f0d8052c3508005f2f974f7f79351c8ffd312cdbab57228 +size 2948281856 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ2_S.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ2_S.gguf new file mode 100644 index 0000000..ec14c6f --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4913a56d2a8e24474ea557dc453551a30bc360f5e27d10df3fe3824407f42ce +size 2758489600 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ2_XS.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ2_XS.gguf new file mode 100644 index 0000000..910e04a --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d54e0820dd7c660eb3a72da00d2acbf5fb6f10b9fc9baeeb166be81e70860a11 +size 2605782528 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ2_XXS.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..2f7c1da --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d2dc675acf9816fe3746a708ab3b4c6214b9075e01a127347f855ac2fd0fbc4 +size 2399213056 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ3_M.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ3_M.gguf new file mode 100644 index 0000000..08f1393 --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d9847a22512767bf840674c3794fb6b6d008be360242a184b290d71667fd683 +size 3784824320 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ3_S.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ3_S.gguf new file mode 100644 index 0000000..74c1ad2 --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94b19e3a904042533582828f5a8bfb42dce30b3daf95f4ba599435a32de2ecc5 +size 3682326016 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ3_XS.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ3_XS.gguf new file mode 100644 index 0000000..36b70a5 --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf131aad7157eaad780dc7735be8f80d88ff277afa5f88d93d7b59e705b7468f +size 3518748160 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ3_XXS.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..043915b --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68978c8b87a9656c42ee66938f82da9cdaf2283a13ac1f5bda7f3e0035db5157 +size 3274913280 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ4_XS.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ4_XS.gguf new file mode 100644 index 0000000..e4e7893 --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9f27d6f9549ecea9a88b16d44c5e301ea958e9ba6c471119921dab920705867 +size 4447663616 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q2_K.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q2_K.gguf new file mode 100644 index 0000000..2dcd7ed --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b2a6a55182feea7a572dcecbad79be67c1446889b180bbe4a50b00f47509bdd +size 3179132416 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q3_K_L.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q3_K_L.gguf new file mode 100644 index 0000000..7bf934e --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7c8d5be5d889eea96313640c6a017325796cbe6bef2c3d6655cb58c64a445ba +size 4321957376 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q3_K_M.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q3_K_M.gguf new file mode 100644 index 0000000..51889fb --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9900d172930f37faffe0e94ff132ed565c297745aa4c802413dda2c2c9aae0d +size 4018918912 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q3_K_S.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q3_K_S.gguf new file mode 100644 index 0000000..67171d7 --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98a9befedeba09735525fcef6ffd981d863f5754e51a4f6b17900d829aba656a +size 3664500224 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_0.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_0.gguf new file mode 100644 index 0000000..705d84b --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d92c6b1852940c819ff2e0f841053b1fda32424c47c1fbb1f49d6721b9084a6 +size 4675892736 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_0_4_4.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..24b0b8c --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93a8930fa54877b758caa45119b723262ff236aaca74097e1e4042537e085d4a +size 4661212672 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_0_4_8.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..fca78c1 --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f12fb7238ba1a0e7c20d54cde2fed8172ef73bf864bdc30a768a54deea1ecd39 +size 4661212672 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_0_8_8.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..2fd30ab --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9edeb5d6ae82768bb336853bba267762c03fad530b8bcea49328e1c9ab678d7a +size 4661212672 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_K_M.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_K_M.gguf new file mode 100644 index 0000000..76ab66b --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6df4311f38360241467a91d0f8ecc60bc217ed11b407e92de7dcc4501adea716 +size 4920735232 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_K_S.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_K_S.gguf new file mode 100644 index 0000000..6398baa --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb3ba0c8230d45215d9916c9de18581f6f837a7c7cd9cd40822c713a462c2938 +size 4692669952 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q5_K_M.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q5_K_M.gguf new file mode 100644 index 0000000..c0f2578 --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c6c9ce2eef68f372612e6da116ba95448142e266304c51262205d6b09ce8e68 +size 5732988416 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q5_K_S.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q5_K_S.gguf new file mode 100644 index 0000000..f931803 --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:610b710d3f6abbfb70e0f432a783840a1f1a99be0690b0397e923d8c593f2250 +size 5599294976 diff --git a/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q6_K.gguf b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q6_K.gguf new file mode 100644 index 0000000..aaca189 --- /dev/null +++ b/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae20891ed82950abffb0e591719e80b44ef4a30d401a91b94d2ecd508e4b20b6 +size 6596007424 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a0ab0cf --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2 +language: +- en +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2 + + +static quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-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-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.8 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.8 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ArliAI-RPMax-v1.2-i1-GGUF/resolve/main/Llama-3.1-8B-ArliAI-RPMax-v1.2.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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..1957da9 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58eb6ffd9e4b07e654290eee9f527e6c980115af00d5c0d05ae4beb9027fd5c1 +size 4988157